DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users’ Dynamic Preferences for Information Diffusion Prediction

DyHDGE: Dynamic heterogeneous transaction graph embedding for safety-centric fraud detection in financial scenarios

Information diffusion prediction is a crucial task for comprehending the dissemination process of information. Although this problem has received significant attention recently, most of the state-of-the-arts primarily focus on the modelling of information cascades, while neglecting the implicit social relations between users in the social network and failing to adequately model the interrelations between the user social network and information cascades. To tackle the aforementioned issues, in this work, we propose a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b>ual-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b>tate <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</b>ypergraph <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b>ontrastive <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</b>earning model (DSHCL). Specifically, we first propose to construct a social hypergraph based on the social network to capture the implicit social relations. Then, for capturing the cascade level correlations among users, we generate the dual-state (i.e., static and dynamic) user representations from the user social hypergraph and information cascades. Finally, we exploit contrastive learning to model the interplay between the social network and information cascades by discriminating the dual-state representations generated from them. We conduct an empirical assessment of DSHCL across four publicly available datasets, and the findings underscore the DSHCL's superiority and the efficacy of its components.

We developed a parallel algorithm to improve the cache behavior and overall performance for multiplication of sparse matrices with sparse vectors (SpMSpV), an operation used increasingly in large graph analytics, particularly dynamic graphs in social networks and homeland security applications. The proposed algorithm builds upon the two-phase approach of partitioning the multiplication into a scaling phase and an aggregation phase, to achieve more cache-friendly access patterns individually in each phase [6], [3]. However, to handle dynamic graphs and achieve better load balancing for parallel implementation, we use a combination of private and shared bins, with synchronized access to shared bins to exchange the product terms between the two phases. The new algorithm accumulates product terms in private bins for each thread. The algorithm then performs a bulk transfer between a private bin and a shared bin, when the private bin becomes full. Then results are aggregated from the shared bins. In addition, we employ heuristics to decide the best algorithm for SpMSpV based on the number of nonzeros involved in the operation. When the number of nonzeros is large, it may be better to perform the operation as SpMV (sparse matrix times dense vector) despite the added conversion cost. Also, if the number of nonzeros is low it is advantageous to use a simplified algorithm. We compared our algorithm with existing algorithms for SpMSpV, and our evaluation shows that execution time is reduced by several times when large graphs are considered.

A number of recent studies of information diffusion in social media, both empirical and theoretical, have been inspired by viral propagation models derived from epidemiology. These studies model the propagation of memes, i.e., pieces of information, between users in a social network similarly to the way diseases spread in human society. Importantly, one would expect a meme to spread in a social network amongst the people who are interested in the topic of that meme. Yet, the importance of topicality for information diffusion has been less explored in the literature. Here, we study empirical data about two different types of memes (hashtags and URLs) spreading through the Twitter's online social network. For every meme, we infer its topics and for every user, we infer her topical interests. To analyze the impact of such topics on the propagation of memes, we introduce a novel theoretical framework of information diffusion. Our analysis identifies two distinct mechanisms, namely topical and non-topical, of information diffusion. The non-topical information diffusion resembles disease spreading as in simple contagion. In contrast, the topical information diffusion happens between users who are topically aligned with the information and has characteristics of omplex contagion. Non-topical memes spread broadly among all users and end up being relatively popular. Topical memes spread narrowly among users who have interests topically aligned with them and are diffused more readily after multiple exposures. Our results show that the topicality of memes and users' interests are essential for understanding and predicting information diffusion.

In the intelligence of social things (IoST) paradigm, where interconnected devices and social networks create a dynamic ecosystem, understanding information diffusion is essential. IoST integrates user interactions, device behaviors, and contextual factors, adding complexity to information networks and necessitating accurate prediction models. This work analyses user behavior in terms of both group and individual relationships and presents an information propagation prediction model that combines information propagation topology features with user relationship representations. Information diffusion prediction analyzes patterns of spread in networks to understand and forecast propagation processes. Existing studies emphasize social and dynamic influence relationships within user groups but often neglect user similarity in group relations and intrinsic factors affecting individual sharing decisions. To address these gaps, a novel model is proposed, combining user relationship representations and diffusion topological features. At the group level, a user cooccurrence graph captures similarity relationship, integrating these with diffusion topology to analyze group interactions. At the individual level, user-specific feature representations and influence factor vectors address intrinsic motivations for sharing. Experimental results validate the model’s efficacy, achieving performance improvements on public datasets. On the Memetracker dataset, the model increased MAP@k by 6.54% and hits@k by 2.75%, demonstrating its ability to capture both group and individual dynamics for enhanced diffusion prediction.

Traditional information spread and activation models on social networks, fail to take user interests towards specific content (topics) into account. To this, we propose a predictive topical spreading activation model (TopSPA). Following cues from the well-known spreading activation (SPA) model, we design the TopSPA algorithm to include the affinity of users to given topics. TopSPA utilizes the social connection structures of users, along with their topic affinities, to model the information flow. We use topic-based skew in energy seeding and energy propagation resistance in the network to form our overall information diffusion model. We empirically validate our model on multiple social event datasets on Twitter, predicting information diffusion over the social graph with a high accuracy.

CasTformer: A novel cascade transformer towards predicting information diffusion

Due to the complex and changing interactions in dynamic scenarios, motion forecasting is a challenging problem in autonomous driving. Most existing works exploit static road graphs to characterize scenarios and are limited in modeling evolving spatio-temporal dependencies in dynamic scenarios. In this letter, we resort to dynamic heterogeneous graphs to model the scenario. Various scenario components including vehicles (agents) and lanes, multi-type interactions, and their changes over time are jointly encoded. Furthermore, we design a novel heterogeneous graph convolutional recurrent network, aggregating diverse interaction information and capturing their evolution, to learn to exploit intrinsic spatio-temporal dependencies in dynamic graphs and obtain effective representations of dynamic scenarios. Finally, with a motion forecasting decoder, our model predicts realistic and multi-modal future trajectories of agents and outperforms state-of-the-art published works on several motion forecasting benchmarks.

Graphs are integral to model real-world complex systems like social networks, citation networks, transaction networks etc. Real-world graphs are mostly heterogeneous, continuously evolving dynamic graphs (i.e. Heterogeneous continuous-time dynamic graph - HCTDG). Modeling HCTDGs requires effective representation learning, which is difficult because of their entangled structural and temporal dependencies. We introduce HT-Graph, a novel framework aimed to improve link prediction in HCTDG graphs. HT-Graph addresses scalability and computational inefficiencies while focusing on enhancing link prediction accuracy. As formation of new links between nodes depends on their neighborhood, HT-Graph introduces a neighbor-aware memory module (i.e. memory module with a neighbor-store) that stores and updates local neighborhood information of each node efficiently for faster calculation of structural information, eliminating redundant computations required for traditional neighborhood sampling. To introduce parallelism, we used a neighbor-aware restarter to restart the training at any timestamp using interaction history. During training, the restarter module resets memory states at multiple timestamps and learns to mimic the encoder through the knowledge distillation process. This eliminates sequential dependencies, enabling HT-Graph to capture temporal dynamics and structural heterogeneity while ensuring scalability. HT-Graph outperforms state-of-the-art models in link prediction, providing higher scalability, efficiency, and better predictive performance even with limited data.

Graph Convolutional Networks (GCNs) have been widely used for collaborative filtering, due to their effectiveness in exploiting high-order collaborative signals. However, two issues have not been well addressed by existing studies. First, usually only one kind of information is utilized, i.e., user preference in user-item graphs or item dependency in item-item graphs. Second, they usually adopt static graphs, which cannot retain the temporal evolution of the information. These can limit the recommendation quality. To address these limitations, we propose to mine three kinds of information (user preference, item dependency, and user behavior similarity) and their temporal evolution by constructing multiple discrete dynamic heterogeneous graphs (i.e., a user-item dynamic graph, an item-item dynamic graph, and a user-subseq dynamic graph) from interaction data. A novel network (PDGCN) is proposed to learn the representations of users and items in these dynamic graphs. Moreover, we designed a structural neighbor aggregation module with novel pooling and convolution operations to aggregate the features of structural neighbors. We also design a temporal neighbor aggregation module based on self-attention mechanism to aggregate the features of temporal neighbors. We conduct extensive experiments on four real-world datasets. The results indicate that our approach outperforms several competing methods in terms of Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG). Dynamic graphs are also shown to be effective in improving recommendation performance.

Graphs are essential representations of many real-world data such as social networks. Recent years have witnessed the increasing efforts made to extend the neural network models to graph-structured data. These methods, which are usually known as the graph neural networks, have been applied to advance many graphs related tasks such as reasoning dynamics of the physical system, graph classification, and node classification. Most of the existing graph neural network models have been designed for static graphs, while many real-world graphs are inherently dynamic. For example, social networks are naturally evolving as new users joining and new relations being created. Current graph neural network models cannot utilize the dynamic information in dynamic graphs. However, the dynamic information has been proven to enhance the performance of many graph analytic tasks such as community detection and link prediction. Hence, it is necessary to design dedicated graph neural networks for dynamic graphs. In this paper, we propose DGNN, a new {\bf D}ynamic {\bf G}raph {\bf N}eural {\bf N}etwork model, which can model the dynamic information as the graph evolving. In particular, the proposed framework can keep updating node information by capturing the sequential information of edges (interactions), the time intervals between edges and information propagation coherently. Experimental results on various dynamic graphs demonstrate the effectiveness of the proposed framework.

In the intelligent transportation system, traffic forecasting, which is generally characterized as a graph spatial-temporal prediction task, plays a crucial role. It is challenging to generate reliable forecast results due to the complexity of traffic topological information and the inherent uncertainty of road traffic circumstances. Existing works generally focus on modeling spatial dependency on static graph structures, but ignore dynamic relations between road segments and cannot extract long-range traffic dependencies in spatial-temporal domains. To bridge the above gaps, we present a novel framework, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Dynamic Multi-Hop Graph Attention Network</i> (DMGAN). Specifically, we leverage dynamic graph modeling to capture time-varying relations across road sections and introduce the multi-hop operation in each message propagation layer to extract long-range spatial dependency. Meanwhile, we develop a fusion-attention module, preserving both local and global hidden layer outputs of the encoder, to capture both long- and short-term temporal dependencies jointly. In this way, our method can fully model complex time-varying traffic topology information and capture the internal patterns of traffic series by integrating dynamic graph structure and temporal attention component. DGMAN achieves state-of-the-art performance in three metrics, as demonstrated by experimental findings on four real-world public traffic datasets, METR-LA, PEMS-BAY, PEMS03, and PEMS07. This code and data are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/EEHITer/2022-TKDE-DMGAN-Pytorch/tree/main</uri> for reproducibility and further studies.

Recently, graph neural networks (GNNs) have been improved under the influence of various deep learning techniques, such as attention, autoencoders, and recurrent networks. However, real-world graphs may have multiple types of vertices and edges, such as graphs of social networks, citation networks, and e-commerce data. In these cases, most GNNs that consider a homogeneous graph as input data are not suitable because they ignore the heterogeneity. Meta-path-based methods have been researched to capture both heterogeneity and structural information of heterogeneous graphs. As a meta-path is a type of graph pattern, we extend the use of meta-paths to exploit graph patterns. In this study, we propose TP-HAN, a heterogeneous graph attention network for exploiting triangle patterns. In the experiments using DBLP and IMDB, we show that TP-HAN outperforms the state-of-the-art heterogeneous graph attention network.KeywordsGraph neural networksHeterogeneous graphTriangle

The rapid growth of social networks and online platforms has heightened the importance of trust evaluation in various applications, including e-commerce, social networking, online collaboration, and mobile crowdsourcing. Traditional trust evaluation methods often rely on handcrafted features and simple models, which fail to fully capture the implicit patterns within the complex, heterogeneous structures of social networks. To address this issue, we propose TrustGTN, a novel method based on Heterogeneous Graph Neural Networks (HGNNs). It incorporates a soft selection mechanism that dynamically adjusts the training matrix weights. This enables it to capture the evolving structural and semantic patterns of the graph. The model can automatically learn important trust chains without the need to manually set their lengths. Experimental results show that TrustGTN outperforms existing trust evaluation methods on public datasets, demonstrating its advantages in handling heterogeneous graph data.

An adapted modeling and visualization technique of links and interactions between several objects,e.g. customers and products, social network and etc,is a precious mean to permit a good understanding of a lot of situations in the enterprise's context. In this latter context, most of the time, these objects and their relations are stored in relational databases. But extracting and modeling heterogeneous graphs from databases are outside of the classical graph models possibilities, moreover when each node contains a set of values. On the other hand, graph models can be a natural way to present these graphs and facilitates their query. In this way, we propose a graph model named SPIDER-Graph which is adapted to represent interactions between complex heterogeneous objects extracted from a relational database. This model is used in our approach of heterogeneous object graph extraction from a relational database which is detailed in this paper.