Types Of Embeddings Research Articles

Learning General and Specific Embedding with Transformer for Few-Shot Object Detection

AbstractFew-shot object detection (FSOD) studies how to detect novel objects with few annotated examples effectively. Recently, it has been demonstrated that decent feature embeddings, including the general feature embeddings that are more invariant to visual changes and the specific feature embeddings that are more discriminative for different object classes, are both important for FSOD. However, current methods lack appropriate mechanisms to sensibly cooperate both types of feature embeddings based on their importance to detecting objects of novel classes, which may result in sub-optimal performance. In this paper, to achieve more effective FSOD, we attempt to explicitly encode both general and specific feature embeddings using learnable tensors and apply a Transformer to help better incorporate them in FSOD according to their relations to the input object features. We thus propose a Transformer-based general and specific embedding learning (T-GSEL) method for FSOD. In T-GSEL, learnable tensors are employed in a three-stage pipeline, encoding feature embeddings in general level, intermediate level, and specific level, respectively. In each stage, we apply a Transformer to first model the relations of the corresponding embedding to input object features and then apply the estimated relations to refine the input features. Meanwhile, we further introduce cross-stage connections between embeddings of different stages to make them complement and cooperate with each other, delivering general, intermediate, and specific feature embeddings stage by stage and utilizing them together for feature refinement in FSOD. In practice, a T-GSEL module is easy to inject. Extensive empirical results further show that our proposed T-GSEL method achieves compelling FSOD performance on both PASCAL VOC and MS COCO datasets compared with other state-of-the-art approaches.

A Whitney Type Theorem for Surfaces: Characterising Graphs with Locally Planar Embeddings

AbstractGiven a graph G and a parameter r, we define the r-local matroid of G to be the matroid generated by its cycles of length at most r. Extending Whitney’s abstract planar duality theorem from 1932, we prove that for every r the r-local matroid of G is co-graphic if and only if G admits a certain type of embedding in a surface, which we call r-planar embedding. The maximum value of r such that a graph G admits an r-planar embedding is closely related to face-width, and such embeddings for this maximum value of r are quite often embeddings of minimum genus. Unlike minimum genus embeddings, these r-planar embeddings can be computed in polynomial time. This provides the first systematic and polynomially computable method to construct for every graph G a surface so that G embeds in that surface in an optimal way (phrased in our notion of r-planarity).

Negative Type and Bi-lipschitz Embeddings into Hilbert Space

The usual theory of negative type (and p-negative type) is heavily dependent on an embedding result of Schoenberg, which states that a metric space isometrically embeds in some Hilbert space if and only if it has 2-negative type. A generalisation of this embedding result to the setting of bi-lipschitz embeddings was given by Linial, London and Rabinovich. In this article we use this newer embedding result to define the concept of distorted p-negative type and extend much of the known theory of p-negative type to the setting of bi-lipschitz embeddings. In particular we show that a metric space (X,dX)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(X,d_{X})$$\\end{document} has p-negative type with distortion C (0≤p<∞\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0\\le p<\\infty $$\\end{document}, 1≤C<∞\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1\\le C<\\infty $$\\end{document}) if and only if (X,dXp/2)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(X,d_{X}^{p/2})$$\\end{document} admits a bi-lipschitz embedding into some Hilbert space with distortion at most C. Analogues of strict p-negative type and polygonal equalities in this new setting are given and systematically studied. Finally, we provide explicit examples of these concepts in the bi-lipschitz setting for the bipartite graphs Km,n\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$K_{m,n}$$\\end{document}.

Contextualized dynamic meta embeddings based on Gated CNNs and self-attention for Arabic machine translation

PurposeThe paper aims to enhance Arabic machine translation (MT) by proposing novel approaches: (1) a dimensionality reduction technique for word embeddings tailored for Arabic text, optimizing efficiency while retaining semantic information; (2) a comprehensive comparison of meta-embedding techniques to improve translation quality; and (3) a method leveraging self-attention and Gated CNNs to capture token dependencies, including temporal and hierarchical features within sentences, and interactions between different embedding types. These approaches collectively aim to enhance translation quality by combining different embedding schemes and leveraging advanced modeling techniques.Design/methodology/approachRecent works on MT in general and Arabic MT in particular often pick one type of word embedding model. In this paper, we present a novel approach to enhance Arabic MT by addressing three key aspects. Firstly, we propose a new dimensionality reduction technique for word embeddings, specifically tailored for Arabic text. This technique optimizes the efficiency of embeddings while retaining their semantic information. Secondly, we conduct an extensive comparison of different meta-embedding techniques, exploring the combination of static and contextual embeddings. Through this analysis, we identify the most effective approach to improve translation quality. Lastly, we introduce a novel method that leverages self-attention and Gated convolutional neural networks (CNNs) to capture token dependencies, including temporal and hierarchical features within sentences, as well as interactions between different types of embeddings. Our experimental results demonstrate the effectiveness of our proposed approach in significantly enhancing Arabic MT performance. It outperforms baseline models with a BLEU score increase of 2 points and achieves superior results compared to state-of-the-art approaches, with an average improvement of 4.6 points across all evaluation metrics.FindingsThe proposed approaches significantly enhance Arabic MT performance. The dimensionality reduction technique improves the efficiency of word embeddings while preserving semantic information. Comprehensive comparison identifies effective meta-embedding techniques, with the contextualized dynamic meta-embeddings (CDME) model showcasing competitive results. Integration of Gated CNNs with the transformer model surpasses baseline performance, leveraging both architectures' strengths. Overall, these findings demonstrate substantial improvements in translation quality, with a BLEU score increase of 2 points and an average improvement of 4.6 points across all evaluation metrics, outperforming state-of-the-art approaches.Originality/valueThe paper’s originality lies in its departure from simply fine-tuning the transformer model for a specific task. Instead, it introduces modifications to the internal architecture of the transformer, integrating Gated CNNs to enhance translation performance. This departure from traditional fine-tuning approaches demonstrates a novel perspective on model enhancement, offering unique insights into improving translation quality without solely relying on pre-existing architectures. The originality in dimensionality reduction lies in the tailored approach for Arabic text. While dimensionality reduction techniques are not new, the paper introduces a specific method optimized for Arabic word embeddings. By employing independent component analysis (ICA) and a post-processing method, the paper effectively reduces the dimensionality of word embeddings while preserving semantic information which has not been investigated before especially for MT task.

Graph Representation Learning for Street-Level Crime Prediction

In contemporary research, the street network emerges as a prominent and recurring theme in crime prediction studies. Meanwhile, graph representation learning shows considerable success, which motivates us to apply the methodology to crime prediction research. In this article, a graph representation learning approach is utilized to derive topological structure embeddings within the street network. Subsequently, a heterogeneous information network that incorporates both the street network and urban facilities is constructed, and embeddings through link prediction tasks are obtained. Finally, the two types of high-order embeddings, along with other spatio-temporal features, are fed into a deep neural network for street-level crime prediction. The proposed framework is tested using data from Beijing, and the outcomes demonstrate that both types of embeddings have a positive impact on crime prediction, with the second embedding showing a more significant contribution. Comparative experiments indicate that the proposed deep neural network offers superior efficiency in crime prediction.

Molecular sequence classification using efficient kernel based embedding

The alarming spread of diseases across the globe has become a major concern for global healthcare agencies. The research community is actively involved in inventing better and more efficient ways of detecting and treating diseases to solve this global challenge. The abundance of molecular sequence data has eased the path for researchers to develop Machine Learning (ML) based solutions. The performance of the ML models used to classify molecular sequences depends heavily on the type of embedding used to obtain an appropriate numerical representation of the molecular sequences. In recent years, many embedding approaches have been introduced for molecular sequence analysis. However, there is still a need for improvement as far as the efficiency of the methods is concerned (i.e., the ability to capture pairwise relationships and patterns effectively, which could affect the classification performance). To provide a solution to this problem, we propose an efficient kernel-based technique for embedding generation from molecular sequences, which involves computing a kernel matrix using the Sinkhorn-Knopp algorithm and the normalized pairwise distances between k-mers in a manner that satisfies the constraints of a probability distribution. Further, kernel principal component analysis (PCA) is applied to get the top PCs, which are then used as the final embedding. As a result of the experiments, we obtained an ROC-AUC score of 0.657 for our method, which is higher than the scores obtained using baselines. This clearly shows that the low-dimensional embedding obtained through the proposed approach provides an efficient and effective solution for molecular sequence analysis.

Potential factors-embedding group recommendation for online education

Online education platform urgently needs recommendation methods to service learning groups. The existing group recommendation methods rely on member preference aggregation. However, potential factors such as teachers and schools have an important impact on the decision-making of learning groups. Due to the different ways in which potential factors operate, it is very challenging to model the impact these potential factors have on groups. In this paper, we propose a group recommendation method for online education (GEMst) that innovatively designs two modules to capture different types of potential factor embedding. In the subjective guidance module, we construct a heterogeneous information network based on the relationship between guiders (teacher, leader, etc.) and groups, analyze the influence of the guider on the group, and obtain the group representation from this perspective. In the objective environment hypergraph module, we consider the influence mode of the environment (school, platform, etc.) on the group, and propose the objective relationship hypergraph convolution. Compared with hypergraph convolution, it directly learns the influence between groups in the same environment. We provide information fusion strategies that GEMst can collaboratively consider group members’ opinions and the impact of potential factors. In addition, to enhance the learning effect of the model, we design a pre-training strategy based on the user grouping relationship that obtains more accurate user embedding representations. We test GEMst on two real-world datasets, and the results show that GEMst outperforms the current baseline group recommendation method.

Pretraining of attention-based deep learning potential model for molecular simulation

Machine learning-assisted modeling of the inter-atomic potential energy surface (PES) is revolutionizing the field of molecular simulation. With the accumulation of high-quality electronic structure data, a model that can be pretrained on all available data and finetuned on downstream tasks with a small additional effort would bring the field to a new stage. Here we propose DPA-1, a Deep Potential model with a gated attention mechanism, which is highly effective for representing the conformation and chemical spaces of atomic systems and learning the PES. We tested DPA-1 on a number of systems and observed superior performance compared with existing benchmarks. When pretrained on large-scale datasets containing 56 elements, DPA-1 can be successfully applied to various downstream tasks with a great improvement of sample efficiency. Surprisingly, for different elements, the learned type embedding parameters form a spiral in the latent space and have a natural correspondence with their positions on the periodic table, showing interesting interpretability of the pretrained DPA-1 model.

Temporal validity reassessment: commonsense reasoning about information obsoleteness

It is useful for machines to know whether text information remains valid or not for various applications including text comprehension, story understanding, temporal information retrieval, and user state tracking on microblogs as well as via chatbot conversations. This kind of inference is still difficult for current models, including also large language models, as it requires temporal commonsense knowledge and reasoning. We approach in this paper the task of Temporal Validity Reassessment, inspired by traditional natural language reasoning to determine the updates of the temporal validity of text content. The task requires judgment whether actions expressed in a sentence are still ongoing or rather completed, hence, whether the sentence still remains valid or has become obsolete, given the presence of context in the form of a supplementary content such as a follow-up sentence. We first construct our own dataset for this task and train several machine learning models. Then we propose an effective method for learning information from an external knowledge base that gives information regarding temporal commonsense knowledge. Using our prepared dataset, we introduce a machine learning model that incorporates the information from the knowledge base and demonstrate that incorporating external knowledge generally improves the results. We also experiment with different embedding types to represent temporal commonsense knowledge as well as with data augmentation methods to increase the size of our dataset.

On the boundary conditions for a thin circular plate conjugated to a massive body

The problem of deformation under the action of uniform pressure of a circular plate coupled with a massive base is considered, while the condition for the coupling of the plate with the base is modeled using boundary conditions of the generalized elastic embedding type, i.e. the relationship between the bending moment and forces at the edge of the plate with displacements and rotation angles through the compliance matrix. The main goal of the work is to study the influence of the elasticity of the embedding on the elastic response of the plate. The solution to the problem was obtained in the formulation of the linear theory of plates, the theory of membranes in the approximation of homogeneity of longitudinal forces, and the Foppl — von Karman theory, also in the approximation of the assumption of homogeneity of longitudinal forces. The values of the coefficients of the compliance matrix were obtained using the finite element method for the auxiliary problem and compared with the values of the coefficients obtained for related problems by analytical methods. Numerical results were obtained for an aluminum wafer on a silicon base. The obtained solution was compared with the solution obtained for the rigid embedment condition for all three models used. It is shown that in the case of large deflections (several plate thicknesses), taking into account the compliance of the embedment becomes essential.

BioBBC: a multi-feature model that enhances the detection of biomedical entities

The rapid increase in biomedical publications necessitates efficient systems to automatically handle Biomedical Named Entity Recognition (BioNER) tasks in unstructured text. However, accurately detecting biomedical entities is quite challenging due to the complexity of their names and the frequent use of abbreviations. In this paper, we propose BioBBC, a deep learning (DL) model that utilizes multi-feature embeddings and is constructed based on the BERT-BiLSTM-CRF to address the BioNER task. BioBBC consists of three main layers; an embedding layer, a Long Short-Term Memory (Bi-LSTM) layer, and a Conditional Random Fields (CRF) layer. BioBBC takes sentences from the biomedical domain as input and identifies the biomedical entities mentioned within the text. The embedding layer generates enriched contextual representation vectors of the input by learning the text through four types of embeddings: part-of-speech tags (POS tags) embedding, char-level embedding, BERT embedding, and data-specific embedding. The BiLSTM layer produces additional syntactic and semantic feature representations. Finally, the CRF layer identifies the best possible tag sequence for the input sentence. Our model is well-constructed and well-optimized for detecting different types of biomedical entities. Based on experimental results, our model outperformed state-of-the-art (SOTA) models with significant improvements based on six benchmark BioNER datasets.

Contrastive domain-adaptive graph selective self-training network for cross-network edge classification

The performance of graph Neural Network (GNNs) can degrade significantly when trained on the graphs with noisy edges connecting nodes from different classes. To mitigate the negative effect of noisy edges, previous studies have largely focused on predicting the label agreement between node pairs within a single network. So far, predicting noisy edges across different networks remains largely underexplored. To bridge this gap, our work studies a novel problem of cross-network homophilous and heterophilous edge classification (CNHHEC), aiming to predict the label agreement of edges in an unlabeled target network by transferring the knowledge from a labeled source network. A novel Contrastive Domain-adaptive Graph Self-training Network (CDGSN) is proposed. Firstly, CDGSN learns node and edge embeddings end-to-end by a GNN encoder with adaptive edge weights during neighborhood aggregation. Secondly, to facilitate knowledge transfer across networks, CDGSN employs an adversarial domain adaptation module to align edge embeddings across networks, and also designs a novel contrastive domain adaptation module to conduct class-aware cross-network alignment of node embeddings. As a result, the intra-class domain divergence can be mitigated while the inter-class domain discrepancy can be enlarged to yield network-invariant and label-discriminative node and edge embeddings. Moreover, CDGSN designs a selective positive and negative pseudo-labeling strategy to assign positive (negative) pseudo-labels to the target nodes with extremely high (low) prediction confidence of belonging to each specific class. Such pseudo-labeled target nodes would be employed to iteratively re-train the model in a self-training manner, so as to obtain more reliable target pseudo-labels progressively to guide class-aware domain alignment. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed CDGSN on the CNHHEC problem. The performance of CDGSN is robust against various types of edge embeddings. When adopting three operators to construct edge embeddings, the proposed CDGSN can improve the state-of-the-art method for CNHHEC by an average of 0.5 %, 2.8 %, and 10.8 % in terms of AUC, and 1.3 %, 3.0 %, and 6.3 % in terms of AP, respectively.

Efficient Malware Analysis Using Metric Embeddings

Real-world malware analysis consists of a complex pipeline of classifiers and data analysis—from detection to classification of capabilities to retrieval of unique training samples from user systems. In this article, we aim to reduce the complexity of these pipelines through the use of low-dimensional metric embeddings of Windows PE files, which can be used in a variety of downstream applications, including malware detection, family classification, and malware attribute tagging. Specifically, we enrich labeling of malicious and benign PE files with computationally-expensive, disassembly-based malicious capabilities information. Using this enhanced labeling, we derive several different types of efficient metric embeddings utilizing an embedding neural network trained via contrastive loss, Spearman rank correlation, and combinations thereof. Our evaluation examines performance on a variety of transfer tasks performed on the EMBER and SOREL datasets, demonstrating that low-dimensional, computationally-efficient metric embeddings maintain performance with little decay. This offers the potential to quickly retrain for a variety of transfer tasks at significantly reduced overhead and complexity. We conclude with an examination of practical considerations for the use of our proposed embedding approach, such as robustness to adversarial evasion and introduction of task-specific auxiliary objectives to improve performance on mission critical tasks.

A novel joint extraction model based on cross-attention mechanism and global pointer using context shield window

Relational triple extraction is a critical step in knowledge graph construction. Compared to pipeline-based extraction, joint extraction is gaining more attention because it can better utilize entity and relation information without causing error propagation issues. Yet, the challenge with joint extraction lies in handling overlapping triples. Existing approaches adopt sequential steps or multiple modules, which often accumulate errors and interfere with redundant data. In this study, we propose an innovative joint extraction model with cross-attention mechanism and global pointers with context shield window. Specifically, our methodology begins by inputting text data into a pre-trained RoBERTa model to generate word vector representations. Subsequently, these embeddings are passed through a modified cross-attention layer along with entity type embeddings to address missing entity type information. Next, we employ the global pointer to transform the extraction problem into a quintuple extraction problem, which skillfully solves the issue of overlapping triples. It is worth mentioning that we design a context shield window on the global pointer, which facilitates the identification of correct entities within a limited range during the entity extraction process. Finally, the capability of our model against malicious samples is improved by adding adversarial training during the training process. Demonstrating superiority over mainstream models, our approach achieves impressive results on three publicly available datasets.

A multi-type vulnerability detection framework with parallel perspective fusion and hierarchical feature enhancement

A core problem of vulnerability detection is to detect multi-type vulnerabilities simultaneously by characterizing vulnerabilities of high diversity and complexity in real program source code. Current methods mainly adjust and compromise multiple code representations such as code sequence and code graph based on composite graph. However, sequential features extracted by graph are hardly sufficient to model the contextual semantic associations of the token sequence. Meanwhile, structural features of the code graph extracted by models based on Euclidean Graph Neural Network are difficult to fit the tree-like calling relationships between code lines. These limitations make it difficult to detect diverse vulnerabilities. In addition, most of the existing models ignore the type of code statement, which is closely associated with some specific vulnerability types. In this paper, we propose a Parallelism Framework with Hierarchical feature Enhancement for Multi-type Vulnerability Detection (PFHE-MVD). PFHE-MVD models program code from three parallel perspectives, containing sequence, code graph, and Abstract Syntax Tree statistic. Hyperbolic Graph Convolutional Neural Network is integrated to model the top-down hierarchical calling structure in program code graph through hyperbolic space mapping. Besides, the statement type of code is embedded along with the code text to strengthen the identification ability for different types of vulnerabilities. Experimental results show that PFHE-MVD achieves new state-of-the-art results in multi-type vulnerability detection. PFHE-MVD captures tree-like hierarchical code structure feature and enhances the distinguishing ability for vulnerabilities by code statement type embedding.

SMLP4Rec: An Efficient All-MLP Architecture for Sequential Recommendations

Self-attention models have achieved the state-of-the-art performance in sequential recommender systems by capturing the sequential dependencies among user–item interactions. However, they rely on adding positional embeddings to the item sequence to retain the sequential information, which may break the semantics of item embeddings due to the heterogeneity between these two types of embeddings. In addition, most existing works assume that such dependencies exist solely in the item embeddings, but neglect their existence among the item features. In our previous study, we proposed a novel sequential recommendation model, i.e., MLP4Rec, based on the recent advances of MLP-Mixer architectures, which is naturally sensitive to the order of items in a sequence because matrix elements related to different positions of a sequence will be given different weights in training. We developed a tri-directional fusion scheme to coherently capture sequential, cross-channel, and cross-feature correlations with linear computational complexity as well as much fewer model parameters than existing self-attention methods. However, the cascading mixer structure, the large number of normalization layers between different mixer layers, and the noise generated by these operations limit the efficiency of information extraction and the effectiveness of MLP4Rec. In this extended version, we propose a novel framework – SMLP4Rec for sequential recommendation to address the aforementioned issues. The new framework changes the flawed cascading structure to a parallel mode, and integrates normalization layers to minimize their impact on the model’s efficiency while maximizing their effectiveness. As a result, the training speed and prediction accuracy of SMLP4Rec are vastly improved in comparison to MLP4Rec. Extensive experimental results demonstrate that the proposed method is significantly superior to the state-of-the-art approaches. The implementation code is available online to ease reproducibility.

Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation

Educational content recommendation is a cornerstone of AI-enhanced learning. In particular, to facilitate navigating the diverse learning resources available on learning platforms, methods are needed for automatically linking learning materials, e.g., in order to recommend textbook content based on exercises. Such methods are typically based on semantic textual similarity (STS) and the use of embeddings for text representation. However, it remains unclear what types of embeddings should be used for this task. In this study, we carry out an extensive empirical evaluation of embeddings derived from three different types of models: (i) static embeddings trained using a concept-based knowledge graph, (ii) contextual embeddings from a pre-trained language model, and (iii) contextual embeddings from a large language model (LLM). In addition to evaluating the models individually, various ensembles are explored based on different strategies for combining two models in an early vs. late fusion fashion. The evaluation is carried out using digital textbooks in Swedish for three different subjects and two types of exercises. The results show that using contextual embeddings from an LLM leads to superior performance compared to the other models, and that there is no significant improvement when combining these with static embeddings trained using a knowledge graph. When using embeddings derived from a smaller language model, however, it helps to combine them with knowledge graph embeddings. The performance of the best-performing model is high for both types of exercises, resulting in a mean Recall@3 of 0.96 and 0.95 and a mean MRR of 0.87 and 0.86 for quizzes and study questions, respectively, demonstrating the feasibility of using STS based on text embeddings for educational content recommendation. The ability to link digital learning materials in an unsupervised manner—relying only on readily available pre-trained models—facilitates the development of AI-enhanced learning.

Implementing and embedding Social Prescribing successfully: what works, for whom and in which context?

Background: Integrating healthcare and social care is necessary because a substantial proportion of primary care clients receive unnecessary healthcare (not tailored to their social needs) which can lead to undesirable costs. Social prescribing is an innovative approach for more holistic person-centered care and aims to address clients’ social determinants of health. Often social prescribing services include link workers who support primary care patients to access community and voluntary care services. The aim is to replace the medical approach with a social approach to address patients’ needs. Previous literature has provided basic insights into how social prescribing can be implemented, especially in the early stages of implementation. Though little is known about how social prescribing can be fully embedded. This study provides guiding principles by which social prescribing can be implemented and embedded successfully and identifies which contextual factors and mechanisms influence these guiding principles.&#x0D; Methods: We conducted a Rapid Realist Review to understand what works, for whom in which context. This review consisted of three steps. The first step was to align the research questions with those of health/cure and care organizations. A local reference panel consisting of national organizations gave advice on the research questions and search strategy. Then, based on these questions a systematic search of the international peer-reviewed literature was conducted. Finally, a panel discussion was organized, engaging Dutch health care professionals working with social prescribing, to discuss what the international insights mean for their local contexts. This input helped to refine the literature review’s findings.&#x0D; Results: Preliminary results provided insight into what is needed for implementing and embedding social prescribing after a pilot phase. For example, investing in a change of culture mindset, enabling trust between health/cure and care professionals, creating facilitative conditions for professionals to work with social prescribing in daily practice. In this paper more detailed insights will be presented on the facilitators and barriers mechanisms for implementing and embedding social prescribing in healthcare and how they operate in different contexts. &#x0D; Discussion: Internationally, social prescribing has gained more and more attention, and first implementation best practices have been identified. However, we found that different types of social prescribing interventions were implemented. We will reflect on how the guiding principles relate to the implementation and embedding of these different types of interventions. &#x0D; &#x0D; Conclusion: Implementation and embedding of social prescribing is experienced as challenging, because of local differences in context, such as different populations and the way in which care is organized. The retrieved insights demonstrate which principles can be followed for implementation and embedding of social prescribing, for whom and in which context.&#x0D; Lessons Learned: We developed guiding principles for the embedding of social prescribing, and we provided insight into what this means for the context in the Netherlands.&#x0D; Suggestions for future research: Despite the increase in implementation, there is little knowledge on the effectiveness of social prescribing on health and wellbeing outcomes of patients, and changes in healthcare use. Future research should focus on gaining insight into the effectiveness and impact of social prescribing.&#x0D; &#x0D; &#x0D; &#x0D;

TOWARDS ACCURATE INSTANCE SEGMENTATION IN LARGE-SCALE LIDAR POINT CLOUDS

Abstract. Panoptic segmentation is the combination of semantic and instance segmentation: assign the points in a 3D point cloud to semantic categories and partition them into distinct object instances. It has many obvious applications for outdoor scene understanding, from city mapping to forest management. Existing methods struggle to segment nearby instances of the same semantic category, like adjacent pieces of street furniture or neighbouring trees, which limits their usability for inventory- or management-type applications that rely on object instances. This study explores the steps of the panoptic segmentation pipeline concerned with clustering points into object instances, with the goal to alleviate that bottleneck. We find that a carefully designed clustering strategy, which leverages multiple types of learned point embeddings, significantly improves instance segmentation. Experiments on the NPM3D urban mobile mapping dataset and the FOR-instance forest dataset demonstrate the effectiveness and versatility of the proposed strategy.

‘Many places to call home’: a typology of job embeddedness among internationally relocated workers and its relationship to personal initiative, intent to stay in the host country, and intent to stay in the organization

In recent years, the literature on job embeddedness among internationally relocated workers (IRWs), i.e. diverse individuals who relocated and execute employment abroad, has developed significantly. However, these studies have predominantly relied on a variable-centered approach, which has major shortcomings that have led to inconsistent and potentially misleading results. In this research, we employed a person-centered approach along with Latent Class Analysis (LCA) to discern various types of embedders among IRWs. We also delved into the relationships between these embedding types and the desire to remain in their current employer organizations and countries, and the influence of personal initiative on the emergence of these embedding types. Our data was gathered from a sample of 707 IRWs residing in Germany, France, and the United Kingdom. The findings from the LCA revealed the presence of four distinct embedding types: ‘home country-focused embedders’, ‘host country community-focused embedders’, ‘host country career-focused embedders’, and ‘transnational embedders’. Among them, ‘transnational embedders’ exhibited the strongest intent to stay in both host countries and organizations. Of the two groups embedded in the host country, those whose embeddedness was private life-oriented were more likely to stay than those whose embeddedness was work-focused. Personal initiative significantly predicted embedding types. On the basis of these findings, we derived implications for theory, research, and practice.