Layered Representation Research Articles

The Dialectics of Ethnocultural Positioning: A Historical and Intergenerational Perspective on Georgian Identity Construction

This manuscript explores the dialectical semiotic dynamics of ethnocultural positioning, examining the heterogeneous plurality of social representations through an intergenerational lens. Ethnocultural identity is constructed through several significant semiotic binary oppositions. A novel methodological approach was developed to examine intergenerational dialectic cleavage by analyzing the literary/poetic conversation between distinguished representatives of different historical and ideological epochs. Sociocultural streams are revealed through individual agents’ dialogical literary writings, which embody historical developments that frame the social processes of ethnopositioning. The contradiction between different ethnocultural social representations and ideologies led to the creation of various semiotic binary oppositions, forming the basis for two distinct versions of Georgianness. Dialogical text analysis highlights the significance of the individual level of analysis, revealing microgenetic developments that underpin broader sociocultural dynamics. Cultural values and identities are not static but rather evolve through idiosyncratic reconstructive modifications shaped by new experiences. Ultimately, layers of relevant social representations create a basic dialectical semiotic structure that serves as a foundation for ethnic identity construction.

Leveraging SERS and Transformer Models for Simultaneous Detection of Multiple Pesticides in Fresh Produce.

The widespread use of pesticides in agriculture poses food safety and environmental risks, highlighting the need for rapid detection techniques to mitigate contamination. Surface-enhanced Raman spectroscopy (SERS) coupled with machine learning provides a powerful approach for the detection and quantification of multiple pesticides in agricultural products. This study introduces the SERSFormer-2.0 model, which excels in both multilabel classification and multiregression tasks for pesticide analysis, leveraging the power of transformer-based machine learning architectures. SERSFormer-2.0 employs novel multitask learning approach with task specific feature representation layers, shared multihead attention transformer encoder, and task-specific output layers to detect pesticides and estimate the precise concentrations of each pesticide simultaneously. By utilizing core-shell gold-silver nanoparticles, the model achieves near-perfect performance in identifying and quantifying pesticide residues, with multilabel metrics and regression accuracy demonstrating exceptional reliability (accuracy = 0.999; F1 score = 0.992; precision = 0.990; recall = 0.996). A detailed examination of the Raman spectra reveals the predominant influence of certain pesticides, and the mechanisms behind spectral dominance were elucidated. Our findings underscore the SERSFormer-2.0 model 's robustness and its potential to detect mixed contaminants in agricultural products, enhancing food safety and regulatory practices.

Capturing the Variability of the Nocturnal Boundary Layer through Localized Perturbation Modeling

Abstract A single-column model is used to investigate regime transitions within the stable atmospheric boundary layer, focusing on the role of small-scale fluctuations in wind and temperature dynamics and of turbulence intermittency as triggers for these transitions. Previous studies revealed abrupt near-surface temperature inversion transitions within a limited wind speed range. However, representing these transitions in numerical weather prediction (NWP) and climate models is a known difficulty. To shed light on boundary layer processes that explain these abrupt transitions, the Ekman layer height and its correlation with regime shifts are analyzed. A sensitivity study is performed with several types of perturbations of the wind and temperature tendencies, as well as with the inclusion of intermittent turbulent mixing through a stochastic stability equation. The effect of small fluctuations of the dynamics on regime transitions is thereby quantified. The combined results for all tested perturbation types indicate that small-scale phenomena can drive persistent regime transitions from very to weakly stable regimes, but for the opposite direction, no evidence of persistent regime transitions was found. The inclusion of intermittency prevents the model from getting trapped in the very stable regime, thus preventing the so-called ”runaway cooling”, an issue for commonly used short-tail stability functions. The findings suggest that using stochastic parameterizations of boundary layer processes, either through stochastically perturbed tendencies or parameters, is an effective approach to represent sharp transitions in the boundary layer regimes and is, therefore, a promising avenue to improve the representation of stable boundary layers in NWP and climate models.

Me! Me! Me! Me! A study and comparison of ego network representations

From social networks to brain connectivity, ego networks are a simple yet powerful approach to visualizing parts of a larger graph, i.e. those related to a selected focal node — the so-called “ego”. While surveys and comparisons of general graph visualization approaches exist in the literature, we note (i) the many conflicting results of comparisons of adjacency matrices and node-link diagrams, thus motivating further study, as well as (ii) the absence of such systematic comparisons for ego networks specifically. In this paper, we propose the development of empirical recommendations for ego network visualization strategies. First, we survey the literature across application domains and collect examples of network visualizations to identify the most common visual encodings, namely straight-line, radial, and layered node-link diagrams, as well as adjacency matrices. These representations are then applied to a representative, intermediate-sized network and subsequently compared in a large-scale, crowd-sourced user study in a mixed-methods analysis setup to investigate their impact on both user experience and performance. Within the limits of this study, and contrary to previous comparative investigations of adjacency matrices and node-link diagrams (outside of ego networks specifically), participants performed systematically worse when using adjacency matrices than those using node-link diagrammatic representations. Similar to previous comparisons of different node-link diagrams, we do not detect any notable differences in participant performance between the three node-link diagrams. Lastly, our quantitative and qualitative results indicate that participants found adjacency matrices harder to learn, use, and understand than node-link diagrams. We conclude that in terms of both participant experience and performance, a layered node-link diagrammatic representation appears to be the most preferable for ego network visualization purposes.

Layered Graph Models for the Electric Vehicle Routing Problem With Nonlinear Charging Functions

AbstractElectric vehicle routing problems (EVRPs) involve the routing of a fleet of electric vehicles (EVs) to visit a set of customers while typically minimizing the total travel and charging time. Due to their limited autonomy, EVs may need to recharge their batteries en‐route at charging stations (CSs). Thus, routing decisions also include which CSs to visit, and how much energy to charge during those visits. These decisions are compounded by the fact that charging times follow a nonlinear charging function with respect to the EV's state of charge (SoC). We propose a layered graph representation for the EVRP with nonlinear charging functions (EVRP‐NL). Specifically, the layers correspond to discretized SoC values. Therefore, the arcs' energy consumption is approximated to match those values. We develop two compact formulations based on the layered graph. Furthermore, we introduced two charging policies that facilitate aligning charging duration with practical considerations. Computational results demonstrate the effectiveness of our formulations. Our best formulation effectively handles instances with up to 40 customers. On those instances, compared to the state‐of‐the‐art compact formulation, our formulation solves 13 more instances to optimality with less than half of the computational time. Considering instances solved by both formulations to optimally, the approximation entailed by our formulation yields a 0.94% deviation on average. Since our best performing formulation is compact, it may be readily used by a broad audience. Furthermore, as the majority of algorithms for the EVPR and its variants are heuristics, our formulation could be beneficial in evaluating the performance of these methods.

A single layer representation of the scattered field for multiple scattering problems

The scattering of scalar waves by a set of scatterers is considered. It is proven that the scattered field can be represented as an integral supported by any smooth surface enclosing the scatterers. This is a generalization of the series expansion over spherical harmonics and spherical Bessel functions for spherical geometries. More precisely, given a set of scatterers, the field scattered by any subset can be expressed as an integral over any smooth surface enclosing the given subset alone. It is then possible to solve the multiple scattering problem by using this integral representation instead of an expansion over spherical harmonics. This result is used to develop an extension of the Fast Multipole Method in order to deal with subsets that are not enclosed within non-intersecting balls.

Better together: Automated app review analysis with deep multi-task learning

Context:User reviews of mobile apps provide an important communication channel between developers and users. Existing approaches to automated app review analysis mainly focus on one task (e.g., bug classification task, information extraction task, etc.) at a time, and are often constrained by the manually defined patterns and the ignorance of the correlations among the tasks. Recently, multi-task learning (MTL) has been successfully applied in many scenarios, with the potential to address the limitations associated with app review mining tasks. Objective:In this paper, we propose MABLE, a deep MTL-based and semantic-aware approach, to improve app review analysis by exploiting task correlations. Methods:MABLE jointly identifies the types of involved bugs reported in the review and extracts the fine-grained features where bugs might occur. It consists of three main phases: (1) data preparation phase, which prepares data to allow data sharing beyond single task learning; (2) model construction phase, which employs a BERT model as the shared representation layer to capture the semantic meanings of reviews, and task-specific layers to model two tasks in parallel; (3) model training phase, which enables eavesdropping by shared loss function between the two related tasks. Results:Evaluation results on six apps show that MABLE outperforms ten commonly-used and state-of-the-art baselines, with the precision of 79.76% and the recall of 79.24% for classifying bugs, and the precision of 79.83% and the recall of 80.33% for extracting problematic app features. The MTL mechanism improves the F-measure of two tasks by 3.80% and 4.63%, respectively. Conclusion:The proposed approach provides a novel and effective way to jointly learn two related review analysis tasks, and sheds light on exploring other review mining tasks.

The topology and geometry of neural representations

A central question for neuroscience is how to characterize brain representations of perceptual and cognitive content. An ideal characterization should distinguish different functional regions with robustness to noise and idiosyncrasies of individual brains that do not correspond to computational differences. Previous studies have characterized brain representations by their representational geometry, which is defined by the representational dissimilarity matrix (RDM), a summary statistic that abstracts from the roles of individual neurons (or responses channels) and characterizes the discriminability of stimuli. Here, we explore a further step of abstraction: from the geometry to the topology of brain representations. We propose topological representational similarity analysis, an extension of representational similarity analysis that uses a family of geotopological summary statistics that generalizes the RDM to characterize the topology while de-emphasizing the geometry. We evaluate this family of statistics in terms of the sensitivity and specificity for model selection using both simulations and functional MRI (fMRI) data. In the simulations, the ground truth is a data-generating layer representation in a neural network model and the models are the same and other layers in different model instances (trained from different random seeds). In fMRI, the ground truth is a visual area and the models are the same and other areas measured in different subjects. Results show that topology-sensitive characterizations of population codes are robust to noise and interindividual variability and maintain excellent sensitivity to the unique representational signatures of different neural network layers and brain regions.

A novel interpretable semi-supervised graph learning model for intelligent fault diagnosis of hydraulic pumps

Although deep learning has gained popularity in the field of fault diagnosis, its limitations are also equally apparent, including: (1) heavy reliance on a substantial volume of labeled samples; (2) a lack of interpretability. To confront these issues, this article proposes a novel interpretable semi-supervised graph learning model for intelligent fault diagnosis of hydraulic pumps. A comparison between the raw data and the model's hidden layer representations is conducted to minimize feature loss. The model commences by preliminarily learning fault information that is intermixed with noise, leveraging a substantial corpus of unlabeled data. In response to the intricacy of downstream tasks, an interpretable feature reconstruction module is introduced. This module employs a nonlinear surrogate model to fit and elucidate the learned features, embedding the explanation scores into the features to reconstruct the samples, a process utilized for model fine-tuning. The feature reconstruction module capitalizes on the explanatory power of the surrogate model, guiding the model to concentrate more on features with significant impact. This method not only provides interpretability during model training but also expedites the convergence speed of the model. Finally, two hydraulic pump experiment cases are used to verify the effectiveness of the model, and the results show that our method has obvious advantages in reducing label dependence and increasing model reliability for decision making.

An Exploration of IFLA LRM for Literature Data Representation

The digital humanities have witnessed a clear development in recent years due partly to their adoption of Semantic Web and linked data technologies and the creation of knowledge bases. In this work, we target the creation of an ontology and knowledge base for literature data representation based on the IFLA Library Reference Model (LRM). IFLA LRM is the main model for book-related data, allowing for a fine representation of the various layers that constitute a book. However, by design, it doesn’t deal with some aspects usually available in literature databases, such as information about authors, literary awards or book themes. As a result, LRM requires some extensions to be able to represent ancillary data. Another challenge is the querying of IFLA LRM knowledge bases, with a performance cost that comes with the fine-grained expressivity of the LRM model, which creates longer and therefore typically slower SPARQL queries. In this work, we propose an extension to the IFLA LRM ontology called IFLA LRM* that targets these limitations including a connection to the vocabulary Schema.org and to the taxonomies Thema and Dewey Decimal, and the representation of literary awards. We also present a practical case study on using our extended model to create a Quebec literature knowledge base, discussing the interest of our extensions.

Adaptive structure generation and neuronal differentiation for memory encoding in SNNs

Memory is the core of cognition. The exploration of the memory encoding mechanism or the representation mechanism of information in the Spiking Neural Network (SNN) is the basis for the in-depth study of memory. In this paper, we study the memory encoding mechanism of multilayer SNN models from a biomimetic perspective and explore a method using the high biological likelihood of SNN to enable the network to effectively simulate memory effects. We proposed a series of heuristic neuron-growing connection algorithms and supervised network weight learning algorithms, which were applied to the unsupervised and supervised training process of the presentation layer. These methods optimized the structure of the representation layer, achieved functional differentiation of neurons, and enabled the network to generate differentiated representations for different data modes. Under our algorithm, the proposed model achieves stable convergence with identical pattern inputs, demonstrating distinct representations and sensitivities to different visual modalities. To achieve stable information expression within the network, we conducted various comparative experiments to determine diverse parameters of the complex network. This paper contributes to the development of Brain-inspired Intelligence by bridging the gap between computer science and neuroscience by using simulations to validate biological hypotheses and guide machine learning.

FLAT: Fusing layer representations for more efficient transfer learning in NLP

Parameter efficient transfer learning (PETL) methods provide an efficient alternative for fine-tuning. However, typical PETL methods inject the same structures to all Pre-trained Language Model (PLM) layers and only use the final hidden states for downstream tasks, regardless of the knowledge diversity across PLM layers. Additionally, the backpropagation path of existing PETL methods still passes through the frozen PLM during training, which is computational and memory inefficient. In this paper, we propose FLAT, a generic PETL method that explicitly and individually combines knowledge across all PLM layers based on the tokens to perform a better transferring. FLAT considers the backbone PLM as a feature extractor and combines the features in a side-network, hence the backpropagation does not involve the PLM, which results in much less memory requirement than previous methods. The results on the GLUE benchmark show that FLAT outperforms other tuning techniques in the low-resource scenarios and achieves on-par performance in the high-resource scenarios with only 0.53% trainable parameters per task and 3.2× less GPU memory usagewith BERTbase. Besides, further ablation study is conducted to reveal that the proposed fusion layer effectively combines knowledge from PLM and helps the classifier to exploit the PLM knowledge to downstream tasks. We will release our code for better reproducibility.

An Adaptive Migration Collaborative Network for Multimodal Image Classification.

The multispectral (MS) and the panchromatic (PAN) images belong to different modalities with specific advantageous properties. Therefore, there is a large representation gap between them. Moreover, the features extracted independently by the two branches belong to different feature spaces, which is not conducive to the subsequent collaborative classification. At the same time, different layers also have different representation capabilities for objects with large size differences. In order to dynamically and adaptively transfer the dominant attributes, reduce the gap between them, find the best shared layer representation, and fuse the features of different representation capabilities, this article proposes an adaptive migration collaborative network (AMC-Net) for multimodal remote-sensing (RS) images classification. First, for the input of the network, we combine principal component analysis (PCA) and nonsubsampled contourlet transformation (NSCT) to migrate the advantageous attributes of the PAN and the MS images to each other. This not only improves the quality of images themselves, but also increases the similarity between the two images, thereby reducing the representational gap between them and the pressure on the subsequent classification network. Second, for the interaction on the feature migrate branch, we design a feature progressive migration fusion unit (FPMF-Unit) based on the adaptive cross-stitch unit of correlation coefficient analysis (CCA), which can make the network automatically learn the features that need to be shared and migrated, aiming to find the best shared-layer representation for multifeature learning. And we design an adaptive layer fusion mechanism module (ALFM-Module), which can adaptively fuse features of different layers, aiming to clearly model the dependencies among multiple layers for different sized objects. Finally, for the output of the network, we add the calculation of the correlation coefficient to the loss function, which can make the network converge to the global optimum as much as possible. The experimental results indicate that AMC-Net can achieve competitive performance. And the code for the network framework is available at: https://github.com/ru-willow/A-AFM-ResNet.

PCN: a deep learning approach to jet tagging utilizing novel graph construction methods and Chebyshev graph convolutions

Jet tagging is a classification problem in high-energy physics experiments that aims to identify the collimated sprays of subatomic particles, jets, from particle collisions and ‘tag’ them to their emitter particle. Advances in jet tagging present opportunities for searches of new physics beyond the Standard Model. Current approaches use deep learning to uncover hidden patterns in complex collision data. However, the representation of jets as inputs to a deep learning model have been varied, and often, informative features are withheld from models. In this study, we propose a graph-based representation of a jet that encodes the most information possible. To learn best from this representation, we design Particle Chebyshev Network (PCN), a graph neural network (GNN) using Chebyshev graph convolutions (ChebConv). ChebConv has been demonstrated as an effective alternative to classical graph convolutions in GNNs and has yet to be explored in jet tagging. PCN achieves a substantial improvement in accuracy over existing taggers and opens the door to future studies into graph-based representations of jets and ChebConv layers in high-energy physics experiments. Code is available at https://github.com/YVSemlani/PCN-Jet-Tagging

CC-SMC: Chain coding-based segmentation map lossless compression

A segmentation map, either static or dynamic, refers to a two-dimensional picture that may vary with time and indicates the segmentation label per pixel. Both the semantic map and the occupancy map in video-based point cloud compression (V-PCC) belong to the segmentation map we referred to. The semantic map can work for many machine vision tasks like tracking and has been used as a layer of image representation in some image compression methods. The occupancy map constitutes a part of the point cloud coding bitstream. Since segmentation maps are widely used, how to efficiently compress them is of interest. We propose a segmentation map lossless compression scheme namely CC-SMC, exploiting the nature of segmentation maps that usually contain limited colors and sharp edges. Specifically, we design a chain coding-based scheme combined with quadtree-based block partitioning. For intraframe coding, one block is partitioned recursively with a quadtree structure, until the block contains only one color, is smaller than a threshold, or satisfies the defined chain coding condition. We revise the three-orthogonal chain coding method to incorporate contextual information and design effective intraframe prediction methods. For interframe coding, one block may find a reference block; the chain difference between the current and the reference blocks is coded. We implement the proposed scheme and test it on several different kinds of segmentation maps. Compared with advanced lossless image compression techniques, our proposed scheme obtains more than 10% bits reduction as well as more than 20% decoding time-saving. The code is available at https://github.com/Yang-Runyu/CC-SMC.

Effects of reservoir mechanical properties on induced seismicity during subsurface hydrogen storage.

The intermittent storage of hydrogen in subsurface porous media such as depleted gas fields could be pivotal to a successful energy transition. Numerical simulations investigate the intermittent storage of hydrogen in a porous, depleted subsurface reservoir. Various parametric studies are performed to assess the effect of mechanical properties of the reservoir (i.e. Young's modulus, Poisson's ratio, Biot coefficient and permeability) on the induced fault slip of a single through-going fault that transverses the entire reservoir. Simulations are run using a three-dimensional, finite element, fully coupled hydromechanical code with explicit representations of layers and faults. The effect of the domain mesh refinement and fault mesh refinement on the fault slip versus operation time solution is investigated. The fault is observed to slip in two distinct events, one during the second injection period and one in the third injection period. The fault is not observed to slip during the storage or withdrawal periods. It is found that in order to minimize seismic risk, a reservoir rock with high Young's modulus (>40 GPa), high Poisson's ratio (>0.30) and high Biot coefficient (>0.65) would be preferable for hydrogen storage. Reservoir rocks of low Young's modulus (10-30 GPa), intermediate Poisson's ratio (0.00-0.30) and low-to-intermediate Biot coefficient (0.25-0.65), at high injection rates, were found to have higher potential of inducing large seismic events.This article is part of the theme issue 'Induced seismicity in coupled subsurface systems'.

Molecular set representation learning

Computational representation of molecules can take many forms, including graphs, string encodings of graphs, binary vectors or learned embeddings in the form of real-valued vectors. These representations are then used in downstream classification and regression tasks using a wide range of machine learning models. However, existing models come with limitations, such as the requirement for clearly defined chemical bonds, which often do not represent the true underlying nature of a molecule. Here we propose a framework for molecular machine learning tasks based on set representation learning. We show that learning on sets of atom invariants alone reaches the performance of state-of-the-art graph-based models on the most-used chemical benchmark datasets and that introducing a set representation layer into graph neural networks can surpass the performance of established methods in the domains of chemistry, biology and material science. We introduce specialized set representation-based neural network architectures for reaction-yield and protein–ligand binding-affinity prediction. Overall, we show that the technique we denote molecular set representation learning is both an alternative and an extension to graph neural network architectures for machine learning tasks on molecules, molecule complexes and chemical reactions.

Chinese Named Entity Recognition method based on multi-feature fusion and biaffine

Chinese Named Entity Recognition (CNER) focuses on precisely identifying predefined structural categories in unstructured Chinese text. Most existing CNER models do not consider the unique glyph and pinyin features of Chinese characters, but the rich semantic features hidden behind these features have a good effect on enhancing the judgment ability of language models. At the same time, it is difficult to identify the boundaries of Chinese nested entities, and accurately identifying the boundaries of entities within nested entities is also a difficult problem to solve. We propose a CNER method based on multi-feature fusion technology and biaffine mechanism to address the above issues: In the input representation layer, integrate the glyph and pinyin features of Chinese characters together, intuitively capturing the semantics of Chinese characters. Furthermore, biaffine mechanism has been introduced to provide a comprehensive view of the input on a global scale. This mechanism effectively converts the task of entity recognition into a problem of assigning scores to spans, hence enhancing the precision of identifying entity borders. In order to evaluate the efficacy of the model, a series of experiments were done on three Chinese entity recognition datasets: Resume, MSRA, and People Daily. The experimental results show that the solid boundary can be identified more accurately, and the F1 values of 96.49%, 96.26% and 96.19% are obtained respectively, which has a better recognition effect than the baseline model.

Aspect extraction with enriching word representation and post-processing rules

The detection of mentioned aspects in product reviews is one of the significant and complex tasks in opinion mining. Recently, contextual-based approaches have significantly improved the accuracy of aspect extraction over non-contextual embeddings. However, these approaches are often computationally expensive and time-consuming; thus, applying such heavy models with insufficient resources and within runtime systems is impractical in many realistic scenarios. The present investigation sought an efficient, practical deep-learning-based model that relies on the complementary power of various existing non-contextual embeddings. In this regard, two morphology-based (character and FastText) and two syntax-based (POS and extended dependency skip-gram) embeddings were used alongside a base word embedding (GloVe) to form an enriched word representation layer. The presented model was integrated into the proposed network architecture (extended BiGRU). Finally, two novel post-processing rules were applied to refine the errors in the model's predictions. The proposed model achieved F-scores of 0.86, 0.91, 0.79, and 0.80 for the SemEval 2014 laptop domain and the SemEval 2015–2016 restaurant domain, respectively. Furthermore, the results were validated by comparing the computational and temporal efficiency of the proposed model with seven BERT-family transformers through statistical tests.

Composite attention mechanism network for deep contrastive multi-view clustering

Contrastive learning-based deep multi-view clustering methods have become a mainstream solution for unlabeled multi-view data. These methods usually utilize a basic structure that combines autoencoder, contrastive learning, or/and MLP projectors to generate more representative latent representations for the final clustering stage. However, existing deep contrastive multi-view clustering ignores two key points: (i) the latent representations projecting from one or more layers of MLP or new representations directly obtained from autoencoder fail to mine inherent relationship inner-view or cross-views; (ii) more existing frameworks only employ a one or dual-contrastive learning module, i.e., view- or/and category-oriented, which may result in the lack of communication between latent representations and clustering assignments. This paper proposes a new composite attention framework for contrastive multi-view clustering to address the above two challenges. Our method learns latent representations utilizing composite attention structure, i.e., Hierarchical Transformer for each view and Shared Attention for all views, rather than simple MLP. As a result, the learned representations can simultaneously preserve important features inside the view and balance the contributions across views. In addition, we add a new communication loss in our new dual contrastive framework. The common semantics will be brought into clustering assignments by pushing clustering assignments closer to the fused latent representations. Therefore, our method will provide a higher quality of clustering assignments for the segmentation problem of unlabeled multi-view data. The extensive experiments on several real data demonstrate that the proposed method can achieve superior performance over many state-of-the-art clustering algorithms, especially the significant improvement of an average of 10% on datasets Caltech and its subsets according to accuracy.