Interactive Graphics Research Articles

Spatio-temporal interactive graph convolution network for vehicle trajectory prediction

Vehicle trajectory prediction is crucial in achieving safe and reliable autonomous driving decision-making. The accuracy of the prediction is affected by many different factors, such as the integrity and efficiency of vehicle-to-vehicle (V2V) data transfer, the complex environmental factors of the surrounding roads and the perception range of vehicle sensors. However, most existing methods cannot capture the dynamic interactive information of vehicles at different time steps. In this paper, we propose a Spatio-Temporal Interactive Graph Convolutional Network (STI-GCN) that predicts future trajectories by acquiring spatiotemporal features of vehicles. In the spatial dimension, we construct a kernel function based on spatial autocorrelation and use it as prior knowledge to describe the degree of mutual influence between vehicles in real traffic scenarios. In addition, the Gated Recurrent Unit (GRU) is used to dynamically capture the spatial features of vehicles to solve the dynamic making graph problem of vehicles in the real traffic scene. In the temporal dimension, we use a Convolutional Neural Network (CNN) to extract the temporal feature in the historical trajectory of the vehicle. Finally, we experimented with our method and existing methods on the public Next Generation Simulation (NGSIM) dataset. The experimental results show that the error of our model is reduced by about 10% compared with the state-of-the-art model. And it also improves about 10 times in two key metrics, namely the number of parameters and inference time.

Advanced Timber Construction Industry: A Quantitative Review of 646 Global Design and Construction Stakeholders

There has been a multi-storey timber construction boom since the start of the millennium. While there is now a body of research on trends, benefits, and disadvantages of timber construction, there is not yet literature on the wider market or the impact of stakeholders on it. This research investigates the (i) architects, (ii) engineers, and (iii) manufacturers involved in the realization of 300 contemporary multi-storey timber buildings from an existing survey. The analysis is based on data sourced from stakeholder websites and the building survey. It evaluates the perceived level of timber expertise of stakeholders based on service categorization and stakeholder type and relates them to the buildings they worked on. The research uses quantitative methods to answer qualitative questions on the connection between architectural variety in timber construction and the stakeholders involved. Interconnectivity between stakeholders and projects is visualized in an interactive network graph. The study shows a segmented mass timber market with relatively few impactful design and construction stakeholders, mostly located in central and northern Europe. It also identifies fabricators as the largest group of innovators advancing the industry and enabling the construction of more complex projects. It reveals the importance of collaboration and knowledge sharing for the industry’s growth.

Feature interactive graph neural network for KG-based recommendation

Graph neural network (GNN) is considered as the state-of-art method for KG-based recommendation. However, the existing GNN-based recommendation methods incorporating KG information fail to fully consider interactions between nodes in the process of message passing and aggregating, which will affect the performance improvement of recommendation. To resolve the above limitation, we propose a Feature Interactive Graph Neural Network for KG-based Recommendation (FIKGRec) to explicitly model sophisticated feature interactions from the complex structure of heterogeneous knowledge graph. The overall framework consists of three components: (1) For items, we construct item-KGs where the nodes (entities) denote items and items’ features, and edges represent the relations between entities. Modeling feature interaction can be thus transformed into modeling node (entity) interaction on the knowledge graph. Specifically, we integrate the collaborative signals into the process of KG signals propagation to capture more precise user preferences and then employ the feature entity interaction layer to incorporate the interaction information between entities in the process of neighbor aggregation of entities in item-KG. (2) For users, a preference-aware attention mechanism is designed to obtain the user’s fine-grained preference for items that have been interacted. (3) The final representations of users and items are fed to deep neural network (DNN) to model complex correlations between them. Extensive experiments on three real-world datasets demonstrate the better performance of our FIKGRec framework compared to state-of-the-arts methods.

Knowledge graph preference migration network for recommendation

Knowledge graph (KG) is being introduced into recommender systems in more and more scenarios. However, the previous recommendation methods based on KG usually focus on mining the relative signals between a user and an item, while ignoring the exploration of collaborative signals between users. In addition, the traditional recommendation methods based on KG completely overlooks the discrepancies among users in the modeling process, which will lead to the problem of insufficient information in the obtained cold-start users’ representations. To tackle these, a novel model named Knowledge Graph Preference Migration Network (KGPM) is proposed by us, aiming to address the lack of information in cold-start users’ representations in the knowledge-aware recommendation. To be specific, the method aggregates the representations from a node’s neighborhoods of different hops to renew the node representation on a collaborative knowledge graph (CKG) consisting of a KG and a user–item interaction graph (UIIG), and differentiates the importance of different neighbors via employing an attention mechanism. Next, to achieve preference migration by mining more collaborative signals among users, the neighbor users of the cold-start users should be further propagated in our elaborately constructed user logical interaction space. We apply two datasets accompanying specific scenarios to verify our proposed model, and the experimental results show that KGPM achieves significant improvements over the most advanced baselines.

Demonstrating Portfolio Frontier Formation and the Capital Allocation Line Using Interactive Graphing

This paper shows how to use interactive graphing via scroll bars to create a two-security portfolio frontier and the Capital Allocation Line. The frontier is enhanced via the use of spinners to control the correlation coefficient and the weight of risky assets as well as data labels that track the weight of the stocks along the frontier as a scroll bar is incremented. The VLOOKUP function is incorporated to lookup the calculated expected return and standard deviation of the risky portfolio at a stock weight controlled by a spinner. The purpose of this paper is to aid instructors in explaining the concepts of investment opportunity sets or frontiers, including the efficient and inefficient portions and riskless lending and borrowing to students of investing.

Learning data science methods through a mobile device and full body motion data

This study presents a mobile app that facilitates undergraduate students to learn data science through their own full body motions. Leveraging the built-in camera of a mobile device, the proposed app captures the user and feeds their images into an open-source computer-vision algorithm that localizes the key joint points of human body. As students can participate in the entire data collection process, the obtained motion data is context-rich and personally relevant to them. The app utilizes the collected motion data to explain various concepts and methods in data science under the context of human movements. The app also visualizes the geometric interpretation of data through various visual aids, such as interactive graphs and figures. In this study, we use principal component analysis, a commonly used dimensionality reduction method, as an example to demonstrate the proposed learning framework. Strategies to encompass other learning modules are also discussed for further improvement.

Spatial Models of Piezoproteins and Networks of Protein-Protein Interactions in Trichoplax Animals (Placozoa)

The marine free-living organism Trichoplax (phylum Placozoa) resembles the unicellular amoeba in shape and type of movement. Trichoplax diverged from the main evolutionary tree in the Neoproterozoic Era and is one of the simplest models of a multicellular animal, as well as a strong example of the ensemble of interacting cells in an organism during its development and movement. Two orthologs of mouse Piezo1 protein (6B3R) were found in two Trichoplax haplotypes H1 and H2 as a result of a search for similar sequences in the NCBI databases. Spatial models of the corresponding proteins, XP_002112008.1 and RDD46920.1, were created based on the structural alignment using a 6KG7 (mouse Piezo2) template. The analysis of domain structures was performed, and a limited graph of protein‒protein interactions of the hypothetical mechanosensor XP_002112008.1 was constructed. The possibility of signal transduction from the mechanoreceptor to membrane complexes, cytoplasm and cell nucleus was shown. It is assumed that mechanosensory receptors of Trichoplax are involved in the perception of force stimuli between neighboring cells and the environment. Based on the obtained data, we propose to use the primitive Trichoplax organism as the simplest multicellular model for mechanical and morphogenetic movements.

Graph-Based Non-Sampling for Knowledge Graph Enhanced Recommendation

Knowledge graph (KG) enhanced recommendation, which aims to solve the cold start and explainability in recommender systems, has attracted considerable research interest recently. Existing recommender systems usually focus on implicit feedback such as purchase history without negative feedback. Most of them apply the negative sampling strategy to deal with the implicit feedback data, which may ignore the latent positive user-item interaction. Some other works adopt the non-sampling strategy that treats all non-observed interactions as negative samples and assigns a weight for each negative sample to represent the probability that this sample is a positive sample. However, they use a simple and intuitive weight assignment strategy and cannot catch the latent relationship from all interaction data. To address these problems, we consider graph structure information of both user-item interaction and knowledge graph, and propose a Graph-based Non-Sampling strategy to achieve efficient performance in Knowledge graph enhanced Recommendation (GNSKR). GNSKR utilizes node centrality to significantly improve recommendation performance with low computation cost. Meanwhile, we combine knowledge graph embedding and recommendation task with a local aggregation block, which efficiently catches the high-order connection information in KG enhanced recommendation. Experiments on three datasets show that GNSKR embraces the state-of-the-art with competitive efficiency.

Sylvester Equation Induced Collaborative Representation Learning for Recommendation

For an actual recommendation system, it generally involves a variety of heterogeneous interactive relationships, such as the typical user-user (U2U), item-item (I2I), and user-item (U2I) interaction relationships. With the application of graph neural networks (GNNs) in embedding various interactive relations, recommendation technology has made gratifying progress in recent years, which benefits lot from its powerful ability in relation modeling. However, most of the existing GNN-based methods fail to collaboratively explore the above heterogeneous multiple interactive relationships, including the internal correlations among multiple relationships and the intrinsic association behind different relationships. As a consequence, the user's personalized preference for the items to be recommended will not be well captured. In this paper, we propose a <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</u> ylvester equation induced <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</u> ollaborative <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</u> epresentation <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</u> earning framework (S-CRL) for recommendation system by utilizing the heterogeneous multiple interactive relationships. In particular, we ingeniously define a novel Sylvester equation to associate tactfully the multiple heterogeneous relations together. From the perspective of rating propagation, such Sylvester equation is shown theoretically to be the optimal solution of a local structure sensitive rating propagation function. Additionally, to seek more expressive embeddings about user and item, a layer-wise attention is introduced to aggregate the multi-hop information from U2U and I2I graphs, respectively, so as to promote the aggregation with the corresponding embeddings from the U2I interaction graph. Extensive experiments on three real-world datasets verify that our model achieves more favorable performance over currently representative methods.

Trigonometric Functions and the Sensations of Tone

Music provides an excellent setting for students to explore trigonometric functions in a setting which is independent of their utility in resolving triangles. In this paper, we present several investigations using trigonometric functions to model musical phenomena. From a mathematical technology point of view, most examples require only function graphing and can be explored using a modern interactive graphing application. One example, however, is an excellent application of trigonometric simplification, for which a Computer Algebra System is a useful tool. A final application is suitable for calculus students and provides an exercise in integration by parts. This can be done by hand, or with the aid of an algebra system.

MGMASR: Multi-Graph and Multi-Aspect Neural Network for Service Recommendation in Internet of Services

With the flourishing development of Everything-as-a-Service (EaaS) and Internet of Everything (IoE), Internet of Services (IoS) has recently emerged as a new buzzword in the field of service computing. Providing accurate and personalized service recommendations to users is essential yet highly challenging in IoS, from a sea of services. Besides the severe sparsity of users’ historical behavior data on services, little study has been reported in the literature on fully exploiting multiple relationship networks embedded in IoS. To fill this gap, we propose a novel Multi-Graph and Multi-Aspect neural network-powered method for Service Recommendation in IoS. Graph neural networks (GNNs) and attention mechanism are jointly employed to simultaneously extract information from a collection of heterogeneous knowledge graphs, constructed from historical data recorded in IoS including the user-service interaction graph, the user-user social graph, and the service-mashup graph. Based on the knowledge learned, user-service interactions are scrutinized from multiple aspects to better learn the multiple preferences of users and the multiple characteristics of services, in order to refine their profiles for future recommendation. The results of extensive experiments over the real-world datasets have demonstrated that MGMASR outperforms the baseline methods and can provide service recommendations more accurately for users in IoS.

An interactive graph resource for chemical engineering teaching

Instructors teaching chemical engineering topics have traditionally used graphical methods to explain core concepts and design unit operations. However, with the shift towards online and blended/flexible learning, there is a need to adapt these graphical methods for online use. This paper presents a set of interactive graphs that can be used for fluid flow, separation process, and reaction process unit operations and aims to investigate students' opinions of the interactive graphs and their motivations for using them in their studies. The digital resource developed in the paper is a set of slim single-page applications written in HTML5 & CSS3 with the numerical calculations undertaken in JavaScript (JS). The interactive graphs are embedded into the virtual learning environment (VLE) system Blackboard for two courses, and a paper survey is used to measure students' perceptions towards the interactive graphs and their use of them. The UTAUT2 model is used to analyse the student use of these resources. It is demonstrated that the use of online interactive graphs is popular with the students and the main driving factors are the performance expectancy and the hedonic motivation. Short scaffold questions to help students interact with the graphs are key to their usefulness. Some guidance on the use of interactive graphs is also provided. The interactive graphical resource can be found and used at the Graphical Chemical Engineering Design weblink: https://www.ce.manchester.ac.uk/gced.

Privacy-preserving graph convolution network for federated item recommendation

In traditional recommender systems, we often build models based on a centralized storage of user data, which however will lead to user privacy concerns and risks. In this paper, we study an emerging and important recommendation problem called federated item recommendation (FIR), in which a recommendation model is built with decentralized data of user-item interactions in a privacy-aware manner, i.e., the personal behavior data of each user does not leave the owner. Recently, graph neural network (GNN) has been widely recognized as a state-of-the-art solution for item recommendation with implicit feedback since it is able to model the high-order connectivity between users and items. However, it is very challenging to exploit the high-order connectivity information in a decentralized user-item interaction graph without compromising user privacy. To address that, we propose a GNN-based federated recommendation framework, i.e., privacy-preserving graph convolution network (P-GCN), for the studied problem of FIR. Our P-GCN can leverage the high-order connectivity information like a centralized GCN model such as LightGCN, though it is built using a decentralized user-item graph. To achieve that, we design a novel privacy-preserving graph convolution approach based on secure aggregation and employ item-based user representation to compensate for the performance loss it causes due to the protection of user privacy. Moreover, we improve a group-wise concealing strategy for protecting user privacy. Empirical studies on three datasets show that our P-GCN can achieve similar or even better performance comparing with the non-federated (i.e., centralized) counterpart, and outperforms all the existing federated methods for the studied problem.

The Group Interaction Field for Learning and Explaining Pedestrian Anticipation

Anticipating others’ actions is innate and essential in order for humans to navigate and interact well with others in dense crowds. This ability is urgently required for unmanned systems such as service robots and self-driving cars. However, existing solutions struggle to predict pedestrian anticipation accurately, because the influence of group-related social behaviors has not been well considered. While group relationships and group interactions are ubiquitous and significantly influence pedestrian anticipation, their influence is diverse and subtle, making it difficult to explicitly quantify. Here, we propose the group interaction field (GIF), a novel group-aware representation that quantifies pedestrian anticipation into a probability field of pedestrians’ future locations and attention orientations. An end-to-end neural network, GIFNet, is tailored to estimate the GIF from explicit multidimensional observations. GIFNet quantifies the influence of group behaviors by formulating a group interaction graph with propagation and graph attention that is adaptive to the group size and dynamic interaction states. The experimental results show that the GIF effectively represents the change in pedestrians’ anticipation under the prominent impact of group behaviors and accurately predicts pedestrians’ future states. Moreover, the GIF contributes to explaining various predictions of pedestrians’ behavior in different social states. The proposed GIF will eventually be able to allow unmanned systems to work in a human-like manner and comply with social norms, thereby promoting harmonious human–machine relationships.

M3GAT: A Multi-modal, Multi-task Interactive Graph Attention Network for Conversational Sentiment Analysis and Emotion Recognition

Sentiment and emotion, which correspond to long-term and short-lived human feelings, are closely linked to each other, leading to the fact that sentiment analysis and emotion recognition are also two interdependent tasks in natural language processing (NLP). One task often leverages the shared knowledge from another task and performs better when solved in a joint learning paradigm. Conversational context dependency, multi-modal interaction, and multi-task correlation are three key factors that contribute to this joint paradigm. However, none of the recent approaches have considered them in a unified framework. To fill this gap, we propose a multi-modal, multi-task interactive graph attention network, termed M3GAT, to simultaneously solve the three problems. At the heart of the model is a proposed interactive conversation graph layer containing three core sub-modules, which are: (1) local-global context connection for modeling both local and global conversational context, (2) cross-modal connection for learning multi-modal complementary and (3) cross-task connection for capturing the correlation across two tasks. Comprehensive experiments on three benchmarking datasets, MELD, MEISD, and MSED, show the effectiveness of M3GAT over state-of-the-art baselines with the margin of 1.88%, 5.37%, and 0.19% for sentiment analysis, and 1.99%, 3.65%, and 0.13% for emotion recognition, respectively. In addition, we also show the superiority of multi-task learning over the single-task framework.

Learning from Hierarchical Structure of Knowledge Graph for Recommendation

Knowledge graphs (KGs) can help enhance recommendations, especially for the data-sparsity scenarios with limited user-item interaction data. Due to the strong power of representation learning of graph neural networks (GNNs), recent works of KG-based recommendation deploy GNN models to learn from both knowledge graph and user-item bipartite interaction graph. However, these works have not well considered the hierarchical structure of knowledge graph, leading to sub-optimal results. Despite the benefit of hierarchical structure, leveraging it is challenging since the structure is always partly-observed. In this work, we first propose to reveal unknown hierarchical structures with a supervised signal detection method and then exploit the hierarchical structure with disentangling representation learning. We conduct experiments on two large-scale datasets, of which the results well verify the superiority and rationality of the proposed method. Further experiments of ablation study with respect to key model designs have demonstrated the effectiveness and rationality of our proposed model. The code is available at https://github.com/tsinghua-fib-lab/HIKE .

Multi-information interaction graph neural network for joint entity and relation extraction

Overlap situation where different triplets share entities or relations is a common challenge in joint entity and relation extraction task. On the one hand, there is strong correlation between overlapping triplets. On the other hand, most of the existing large-scale training data come from distant supervision, which introduces incomplete annotations. These practical problems make the information interaction between triplets particularly important. However, there are two problems with the existing methods: (i) the neglect of information interaction between different triplets; (ii) the limited information utilization caused by the specific decoding order. To solve the above problems, we decompose decoding and information interaction. Specifically, entity and relation proposals are obtained by a proposal generator, then a multi-information interaction graph neural network with parallel decoder is proposed to complete the joint extraction task. In this way, the inherent decoding order is broken to achieve the purpose of fully exploiting multi-information interaction across triplets and within triplets. Experimental results show that our proposed model outperforms previous work, especially in the case of incomplete annotations.

Personalized Point-of-Interest Recommendation Using Improved Graph Convolutional Network in Location-Based Social Network

Data sparsity limits the performance of point-of-interest (POI) recommendation models, and the existing works ignore the higher-order collaborative influence of users and POIs and lack in-depth mining of user social influence, resulting in unsatisfactory recommendation results. To address the above issues, this paper proposes a personalized POI recommendation using an improved graph convolutional network (PPR_IGCN) model, which integrates collaborative influence and social influence into POI recommendations. On the one hand, a user-POI interaction graph, a POI-POI graph, and a user–user graph are constructed based on check-in data and social data in a location-based social network (LBSN). The improved graph convolutional network (GCN) is used to mine the higher-order collaborative influence of users and POIs in the three types of relationship graphs and to deeply extract the potential features of users and POIs. On the other hand, the social influence of the user’s higher-order social friends and community neighbors on the user is obtained according to the user’s higher-order social embedding vector learned in the user–user graph. Finally, the captured user and POI’s higher-order collaborative influence and social influence are used to predict user preferences. The experimental results on Foursquare and Yelp datasets indicate that the proposed model PPR_IGCN outperforms other models in terms of precision, recall, and normalized discounted cumulative gain (NDCG), which proves the effectiveness of the model.

LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering

Graph Collaborative Filtering (GCF) methods have emerged as an effective recommendation approach, capturing users’ preferences over items by modeling user–item interaction graphs. However, these methods suffer from data sparsity in real scenarios, and their performance can be improved using contrastive learning. In this paper, we propose an optimized method, named LoRA-NCL, for GCF based on Neighborhood-enriched Contrastive Learning (NCL) and low-rank dimensionality reduction. We incorporate low-rank features obtained through matrix factorization into the NCL framework and employ LightGCN to extract high-dimensional representations. Extensive experiments on five public datasets demonstrate that the proposed method outperforms a competitive graph collaborative filtering base model, achieving 4.6% performance gains on the MovieLens dataset, respectively.

A Review-based Feature-level Information Aggregation Model for Graph Collaborative Filtering

To explicitly exploit the collaborative signals in the user-item interaction graph, a growing number of recent Collaborative Filtering (CF) studies adopt Graph Convolution Network (GCN) as a basis. Though effective, these methods basically treat all neighbors equally, ignoring the fact that neighbors should be target-related. While there are some works that assign different weights to neighbors via using the attention mechanism, they still suffer from two problems. First, the performance of them is limited by the lack of fine-grained details. Second, attention learned solely from interaction data may not reflect the user’s opinions accurately. To address these issues, we propose a Review-based Feature-level Information Aggregation (RFIA) graph model that incorporates the review information into the graph propagation to achieve more fine-grained information aggregation. The main idea of RFIA is to assign feature-level attention vectors for the interaction edges to adaptively adjust the contribution ratios of input neighbors across various dimensions, based on rich review information. Specifically, we first extract review features from text by BERT-Whitening. Then, we design non-linear feature extractors separately in two directions to further extract and refine these review features as feature-level attention. Finally, we design a graph contrastive learning module to optimize the learning of extractors under limited user behaviors. Experiments on three publicly available datasets validate the effectiveness and performance superiority of our proposed model.