Molecular evolution is the process of simulating the natural evolution of molecules in chemical space to explore potential molecular structures and properties. The relationships between similar molecules are often described through transformations such as adding, deleting, and modifying atoms and chemical bonds, reflecting specific evolutionary paths. Existing molecular representation methods mainly focus on mining data, such as atomic-level structures and chemical bonds directly from the molecules, often overlooking their evolutionary history. Consequently, we aim to explore the possibility of enhancing molecular representations by simulating the evolutionary process. We extract and analyze the changes in the evolutionary pathway and explore combining it with existing molecular representations. Therefore, this paper proposes the molecular evolutionary network (MEvoN) for molecular representations. First, we construct the MEvoN using molecules with a small number of atoms and generate evolutionary paths utilizing similarity calculations. Then, by modeling the atomic-level changes, MEvoN reveals their impact on molecular properties. Experimental results show that the MEvoN-based molecular property prediction method significantly improves the performance of traditional end-to-end algorithms by approximately 33% on both the QM7 and QM9 datasets.

The prediction of compound–protein interactions (CPIs) is crucial for drug discovery. Most existing CPI prediction models rely on protein sequence information as input. However, in early-stage drug development, particularly in phenotype-driven studies or compound-response analyses, proteins are often annotated only with functional labels, and their sequences remain undetermined. Consequently, current methods are inapplicable in such scenarios. Furthermore, our experiments find that even when large-scale perturbations were applied to protein sequences, the predictive performance of the existing models did not show a significant decline. It indicates that the high investment in sequencing may not bring corresponding returns. To address the above issues, we propose an inexpensive, protein-sequencing-free framework BioText-CPI, based on the Biomedical Textual description of protein for CPI prediction. Firstly, during the pre-training stage of the model, we use contrastive learning to align protein texts and sequence modalities. Subsequently, we add biological text descriptions of proteins to the existing public CPI dataset to construct a new CPI dataset. Finally, in the CPI prediction stage, the sequence and biomedical text descriptions of proteins can be used as the input for CPI prediction either separately or simultaneously to meet the application requirements of different scenarios. The experiments demonstrate that BioText-CPI achieves comparable effects to the traditional methods when only the biomedical description of protein is input. Moreover, when the two modalities of protein information are input simultaneously, BioText-CPI achieves state-of-the-art performance across multiple scenarios.

Haoran Li, Yulin Chen, Huihao Jing, Wenbin Hu, Tsz Ho Li, Chanhou Lou, Hong Ting Tsang, Sirui Han, Yangqiu Song. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Graph Masked Autoencoders (GMAEs) have emerged as a notable self-supervised learning approach for graph-structured data. Existing GMAE models primarily focus on reconstructing node-level information, categorizing them as single-scale GMAEs. This methodology, while effective in certain contexts, tends to overlook the complex hierarchical structures inherent in many real-world graphs. For instance, molecular graphs exhibit a clear hierarchical organization in the form of the atoms-functional groups-molecules structure. Therefore, the inability of single-scale GMAE models to incorporate these hierarchical relationships often results in an inadequate capture of crucial high-level graph information, leading to a noticeable decline in performance. To address this limitation, we propose Hierarchical Graph Masked AutoEncoders (Hi-GMAE), a novel multi-scale GMAE framework designed to handle the hierarchical structures within graphs. First, Hi-GMAE constructs a multi-scale graph hierarchy through graph pooling, enabling the exploration of graph structures across different granularity levels. To ensure masking uniformity of subgraphs across these scales, we propose a novel coarse-to-fine strategy that initiates masking at the coarsest scale and progressively back-projects the mask to finer scales. Furthermore, we integrate a gradual recovery strategy with the masking process to mitigate the learning challenges posed by completely masked subgraphs. Diverging from the standard graph neural network (GNN) used in GMAE models, Hi-GMAE modifies its encoder and decoder into hierarchical structures. This entails using GNN at the finer scales for detailed local graph analysis and employing a graph transformer at coarser scales to capture global information. Such a design enables Hi-GMAE to effectively capture the multi-level information inherent in complex graph structures. Our experiments on 17 graph datasets, covering two graph learning tasks, consistently demonstrate that Hi-GMAE outperforms 29 state-of-the-art self-supervised competitors in capturing comprehensive graph information.

Brain graphs (brain connectivity networks) play an important role in modeling the complex structure of the human brain. Furthermore, brain graph learning based on graph neural networks (GNNs) has recently attracted growing interest. Although existing methods have made great progress in brain disorder prediction and pathogenic analysis, there are two key problems: (1) They rarely utilize the pathogenic reason of brain disorders, that is, salient brain regions always lead to abnormal connections between brain regions, to extract critical brain graph information for disorder analysis; (2) Since most of the available brain graph data is limited, how can we improve the performance of brain graph learning models on insufficient training data? Thus, in this paper, we learn brain graph representations for disorder prediction and analyze disorder-specific brain regions and connections from the subgraph perspective. Besides, we introduce the cross-domain brain graph learning framework to alleviate the problem of poor model performance on limited data. To consider the pathogenic reason by brain subgraphs, we first propose the node entropy of brain graphs based on brain graph properties to extract important nodes. We then introduce subgraph information bottleneck to refine the critical subgraph from the rough subgraph generated by these important nodes, recognizing important connections related to disorders. To achieve a better model performance on limited data, we design a cross-domain brain graph learning framework to improve the subgraph extraction model by the meta-learning method. The subgraph extraction model is pre-trained on a large source training dataset and then quickly adapted to target task dataset. Besides, a simple yet effective feature alignment module is applied to mitigate the negative transfer problem for cross-domain datasets. Extensive experimental results, including disorder prediction and pathogenic analysis on real-world neuroimaging data, demonstrate the effectiveness of our method.

Haoran Li, Wenbin Hu, Huihao Jing, Yulin Chen, Qi Hu, Sirui Han, Tianshu Chu, Peizhao Hu, Yangqiu Song. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Generating graph-structured molecular data involves understanding complex graph distributions. This is crucial for de novo drug molecule design, especially when incorporating drug-drug interactions (DDIs). Existing graph generative methods often struggle to capture the graphs' permutation invariance or fail to model the collaborative dependencies among various molecular components, including atom-, bond-, and textual-level DDI information. To address these limitations, we propose DDI-Diff, a knowledge-driven dual diffusion model for DDI-based drug design. DDI-Diff employs a continuous time framework and introduces a collaborative graph diffusion process, leveraging a stochastic differential equations (SDEs) system to jointly model node and edge distribution. During pretraining, we use a large-scale, unconditional dataset, followed by conditional training on DrugBank. This enhances the model's ability to generate molecular structures that align with DDI-aware knowledge, effectively capturing the collaborative effects among drugs. Then, we validated our model using DrugBank, demonstrating that DDI-Diff improves accuracy by 4.35% more than current state-of-the-art methods across all labels and highlighting its potential in collaborative drug design.

Wenbin Hu, Haoran Li, Huihao Jing, Qi Hu, Ziqian Zeng, Sirui Han, Xu Heli, Tianshu Chu, Peizhao Hu, Yangqiu Song. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks.Its decentralized architecture, which separates clients and servers, poses unique challenges for systematic safety analysis.This paper proposes a novel framework to enhance MCP safety.Guided by the MAESTRO framework, we first analyze the missing safety mechanisms in MCP, and based on this analysis, we propose the Model Contextual Integrity Protocol (MCIP), a refined version of MCP that addresses these gaps.Next, we develop a fine-grained taxonomy that captures a diverse range of unsafe behaviors observed in MCP scenarios.Building on this taxonomy, we develop benchmark and training data that support the evaluation and improvement of LLMs' capabilities in identifying safety risks within MCP interactions.Leveraging the proposed benchmark and training data, we conduct extensive experiments on state-of-the-art LLMs.The results highlight LLMs' vulnerabilities in MCP interactions and demonstrate that our approach substantially improves their safety performance.1

Due to their excellent drug-like and pharmacokinetic properties, small molecule drugs are widely used to treat various diseases, making them a critical component of drug discovery. In recent years, with the rapid development of deep learning (DL) techniques, DL-based small molecule drug discovery methods have achieved excellent performance in prediction accuracy, speed, and complex molecular relationship modeling compared to traditional machine learning approaches. These advancements enhance drug screening efficiency, streamline optimization, and provide more precise and effective solutions for drug discovery. Contributing to this field's development, this paper aims to systematically summarize and generalize the recent key tasks and representative techniques in graph-structured small molecule drug discovery. Specifically, we provide an overview of the major tasks in small-molecule drug discovery and their interrelationships. Next, we analyze the six core tasks, summarizing the related methods, commonly used datasets, and technological development trends. Finally, we discuss key challenges, such as interpretability and out-of-distribution generalization, and offer our insights into future research directions for small molecule drug discovery.

Antibody design remains a critical challenge in therapeutic and diagnostic development, particularly for complex antigens with diverse binding interfaces. Current computational methods face two main limitations: (1) capturing geometric features while preserving symmetries, and (2) generalizing novel antigen interfaces. Despite recent advancements, these methods often fail to accurately capture molecular interactions and maintain structural integrity. To address these challenges, we propose AbMEGD, an end-to-end framework integrating Multi-scale Equivariant Graph Diffusion for antibody sequence and structure co-design. Leveraging advanced geometric deep learning, AbMEGD combines atomic-level geometric features with residue-level embeddings, capturing local atomic details and global sequence-structure interactions. Its E(3)-equivariant diffusion method ensures geometric precision, computational efficiency, and robust generalizability for complex antigens. Furthermore, experiments using the SAbDab database demonstrate a 10.13% increase in amino acid recovery, 3.32% rise in improvement percentage, and a 0.062 Å reduction in root mean square deviation within the critical CDR-H3 region compared to DiffAb, a leading antibody design model. These results highlight AbMEGD's ability to balance structural integrity with improved functionality, establishing a new benchmark for sequence-structure co-design and affinity optimization. The code is available at: https://github.com/Patrick221215/AbMEGD.

Retrosynthesis prediction aims to infer the precursor compounds and synthetic pathways for the given product molecule. Despite the emergence of numerous data-driven template-free approaches, most rely on single-modality inputs (e.g., SMILES or molecular graphs), limiting them to incorporate multimodal information. Besides, existing methods require complex alignment preprocessing for models to capture unaltered molecular structures in reactions, which rigidly restricts the data format and hinders generalizing to practical application scenarios. To address these challenges, this paper proposes a novel end-to-end template-free learning framework, named Cross-modal Fine-grained Contrastive Learning for Retrosynthesis Prediction (CFC-Retro). By taking both sequence and graph data as inputs, CFC-Retro leverages the cross-attention mechanism to effectively integrate multimodal information during encoding. Additionally, CFC-Retro employs multimodal hybrid-enhanced decoding to produce accurate results. Moreover, the contrastive learning strategy in CFC-Retro implicitly aligns multimodal features at the atomic level. This strategy guides the model to perceive molecular structural changes in chemical reactions, while exhibiting high flexibility. Experiments show that CFC-Retro achieves top-1 accuracy of 53.7% and validity of 99.7% on USPTO-50k with reaction class unknown, underscoring its robust performance in retrosynthesis prediction.

Molecular representation learning is pivotal in predicting molecular properties and advancing drug design. Traditional methodologies, which predominantly rely on homogeneous graph encoding, are limited by their inability to integrate external knowledge and represent molecular structures across different levels of granularity. To address these limitations, we propose a paradigm shift by encoding molecular graphs into heterogeneous structures, introducing a novel framework: Knowledge-aware Contrastive Heterogeneous Molecular Graph Learning. This approach leverages contrastive learning to enrich molecular representations with embedded external knowledge. KCHML conceptualizes molecules through three distinct graph views-molecular, elemental, and pharmacological-enhanced by heterogeneous molecular graphs and a dual message-passing mechanism. This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction prediction. Extensive benchmarking demonstrates KCHML's superiority over state-of-the-art molecular property prediction models, underscoring its ability to capture intricate molecular features.

Node and graph-level clustering hold considerable significance for a wide range of applications, including drug target identification and protein function prediction. Recently, contrastive learning has surpassed numerous unsupervised learning methods and become increasingly useful for various deep clustering procedures, achieving commendable results. However, two primary obstacles impede further deployment of graph contrastive clustering: (1) its inherent tendency to separate node representations, which contradicts the clustering objective of forming meaningful groups and impedes effective cluster creation, and (2) the occurrence of false negative samples, which similarly obstructs cluster formation. Hence, this paper proposes a novel graph clustering algorithm, which employs a dual contrastive learning approach, encompassing element and cluster contrasts, and a strategy for debiasing false negative samples. The proposed algorithm utilizes element-level contrastive learning on embeddings derived from the encoder, integrating detailed node or graph characteristics. Then, clustering and cluster-level contrastive learning are executed in the embedding space to refine the results. Furthermore, the algorithm effectively addresses the potential false negatives and imbalanced prediction challenges during the dual-contrast process by implementing an optimization mechanism based on reliable results, thereby enhancing the clustering performance. Rigorous experiments across three node and graph-level benchmarks validate our proposed algorithm's efficacy.

Graph neural networks (GNNs) tend to suffer from high computation costs due to the exponentially increasing scale of graph data and a large number of model parameters, which restricts their utility in practical applications. To this end, some recent works focus on sparsifying GNNs (including graph structures and model parameters) with the lottery ticket hypothesis (LTH) to reduce inference costs while maintaining performance levels. However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where vast redundancy exists. To overcome the above limitations, we propose a comprehensive graph gradual pruning framework termed CGP. This is achieved by designing a during-training graph pruning paradigm to dynamically prune GNNs within one training process. Unlike LTH-based methods, the proposed CGP approach requires no retraining, which significantly reduces the computation costs. Furthermore, we design a cosparsifying strategy to comprehensively trim all the three core elements of GNNs: graph structures, node features, and model parameters. Next, to refine the pruning operation, we introduce a regrowth process into our CGP framework, to reestablish the pruned but important connections. The proposed CGP is evaluated over a node classification task across six GNN architectures, including shallow models [graph convolutional network (GCN) and graph attention network (GAT)], shallow-but-deep-propagation models [simple graph convolution (SGC) and approximate personalized propagation of neural predictions (APPNP)], and deep models [GCN via initial residual and identity mapping (GCNII) and residual GCN (ResGCN)], on a total of 14 real-world graph datasets, including large-scale graph datasets from the challenging Open Graph Benchmark (OGB). Experiments reveal that the proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of the existing methods.

Detecting a community in a network is a matter of discerning the distinct features and connections of a group of members that are different from those in other communities. The ability to do this is of great significance in network analysis. However, beyond the classic spectral clustering and statistical inference methods, there have been significant developments with deep learning techniques for community detection in recent years-particularly when it comes to handling high-dimensional network data. Hence, a comprehensive review of the latest progress in community detection through deep learning is timely. To frame the survey, we have devised a new taxonomy covering different state-of-the-art methods, including deep learning models based on deep neural networks (DNNs), deep nonnegative matrix factorization, and deep sparse filtering. The main category, i.e., DNNs, is further divided into convolutional networks, graph attention networks, generative adversarial networks, and autoencoders. The popular benchmark datasets, evaluation metrics, and open-source implementations to address experimentation settings are also summarized. This is followed by a discussion on the practical applications of community detection in various domains. The survey concludes with suggestions of challenging topics that would make for fruitful future research directions in this fast-growing deep learning field.

Graph Transformers (GTs) have proved their advantage in graph-level tasks. However, existing GTs still perform unsatisfactorily on the node classification task due to 1) the overwhelming unrelated information obtained from a vast number of irrelevant distant nodes and 2) the quadratic complexity regarding the number of nodes via the fully connected attention mechanism. In this paper, we present Gapformer, a method for node classification that deeply incorporates Graph Transformer with Graph Pooling. More specifically, Gapformer coarsens the large-scale nodes of a graph into a smaller number of pooling nodes via local or global graph pooling methods, and then computes the attention solely with the pooling nodes rather than all other nodes. In such a manner, the negative influence of the overwhelming unrelated nodes is mitigated while maintaining the long-range information, and the quadratic complexity is reduced to linear complexity with respect to the fixed number of pooling nodes. Extensive experiments on 13 node classification datasets, including homophilic and heterophilic graph datasets, demonstrate the competitive performance of Gapformer over existing Graph Neural Networks and GTs.

Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation. As an essential component of the architecture, graph pooling is indispensable for obtaining a holistic graph-level representation of the whole graph. Although a great variety of methods have been proposed in this promising and fast-developing research field, to the best of our knowledge, little effort has been made to systematically summarize these works. To set the stage for the development of future works, in this paper, we attempt to fill this gap by providing a broad review of recent methods for graph pooling. Specifically, 1) we first propose a taxonomy of existing graph pooling methods with a mathematical summary for each category; 2) then, we provide an overview of the libraries related to graph pooling, including the commonly used datasets, model architectures for downstream tasks, and open-source implementations; 3) next, we further outline the applications that incorporate the idea of graph pooling in a variety of domains; 4) finally, we discuss certain critical challenges facing current studies and share our insights on future potential directions for research on the improvement of graph pooling.

Relation Extraction (RE) is a crucial task in Information Extraction, which entails predicting relationships between entities within a given sentence. However, extending pre-trained RE models to other languages is challenging, particularly in real-world scenarios where Cross-Lingual Relation Extraction (XRE) is required. Despite recent advancements in Prompt-Learning, which involves transferring knowledge from Multilingual Pre-trained Language Models (PLMs) to diverse downstream tasks, there is limited research on the effective use of multilingual PLMs with prompts to improve XRE. In this paper, we present a novel XRE algorithm based on Prompt-Tuning, referred to as Prompt-Xre. To evaluate its effectiveness, we design and implement several prompt templates, including hard, soft, and hybrid prompts, and empirically test their performance on competitive multilingual PLMs, specifically mBART. Our extensive experiments, conducted on the low-resource ACE05 benchmark across multiple languages, demonstrate that our Prompt-Xre algorithm significantly outperforms both vanilla multilingual PLMs and other existing models, achieving state-of-the-art performance in XRE. To further show the generalization of our Prompt-XRE on larger data scales, we construct and release a new XRE dataset-WMTI7-EnZh XRE, containing 0.9M English-Chinese pairs extracted from WMT 2017 parallel corpus. Experiments on WMTI7-EnZh XRE also show the effectiveness of our Prompt-XRE against other competitive baselines. The code and newly constructed dataset are freely available at httus://2ithub.com/HSU-CHIA-MING/Promut-XRE.

The introduction of knowledge graphs (KG) into recommendation systems (RS) has been proven to be effective because KG introduces a variety of relations between items. In fact, users have different relation preferences depending on the relationship in KG. Existing GNN-based models largely adopt random neighbor sampling strategies to process propagation; however, these models cannot aggregate biased relation preference local information for a specific user, and thus cannot effectively reveal the internal relationship between users' preferences. This will reduce the accuracy of recommendations, while also limiting the interpretability of the results.

Node classification is a fundamental graph-based task that aims to predict the classes of unlabeled nodes, for which Graph Neural Networks (GNNs) are the state-of-the-art methods. Current GNNs assume that nodes in the training set contribute equally during training. However, the quality of training nodes varies greatly, and the performance of GNNs could be harmed by two types of low-quality training nodes: (1) inter-class nodes situated near class boundaries that lack the typical characteristics of their corresponding classes. Because GNNs are data-driven approaches, training on these nodes could degrade the accuracy. (2) mislabeled nodes. In real-world graphs, nodes are often mislabeled, which can significantly degrade the robustness of GNNs. To mitigate the detrimental effect of the low-quality training nodes, we present CLNode, which employs a selective training strategy to train GNN based on the quality of nodes. Specifically, we first design a multi-perspective difficulty measurer to accurately measure the quality of training nodes. Then, based on the measured qualities, we employ a training scheduler that selects appropriate training nodes to train GNN in each epoch. To evaluate the effectiveness of CLNode, we conduct extensive experiments by incorporating it in six representative backbone GNNs. Experimental results on real-world networks demonstrate that CLNode is a general framework that can be combined with various GNNs to improve their accuracy and robustness.

Multi-task Learning (MTL), which involves the simultaneous learning of multiple tasks, can achieve better performance than learning each task independently. It has achieved great success in various applications, ranging from Computer Vision (CV) to Natural Language Processing (NLP). In MTL, the losses of the including tasks are jointly optimized. However, it is common for these tasks to be competing. When the tasks are competing, minimizing the losses of some tasks increases the losses of others, which accordingly increases the task variance (variance between the task-specific loss); furthermore, it induces under-fitting in some tasks and over-fitting in others, which degenerates the generalization performance of an MTL model. To address this issue, it is necessary to control the task variance; thus, task variance regularization is a natural choice. While intuitive, task variance regularization remains unexplored in MTL. Accordingly, to fill this gap, we study the generalization error bound of MTL through the lens of task variance and propose the task variance matters the generalization performance of MTL. Furthermore, this paper investigates how the task variance might be effectively regularized, and consequently proposes a multi-task learning method based on adversarial multi-armed bandit. The proposed method, dubbed BanditMTL, regularizes the task variance by means of a mirror gradient ascent-descent algorithm. Adopting BanditMTL both in CV and NLP applications is found to achieve state-of-the-art performance. The results of extensive experiments back up our theoretical analysis and validate the superiority of our proposals.

Link prediction has attracted considerable attention. Empiricism and the evolution mechanism based approach are the mainstream methods for link prediction. However, one drawback of such approaches is that they usually ignore the dynamic evolution mechanism of social networks, yet being dynamic is an essential characteristic of a social network that exists in every stage of the networks evolution. In this paper, we address the problem of temporal link prediction and investigate social networks from the time dimension with the purpose of dynamic evolution mechanism capturing. First, we separate a temporal network into a series of snapshots. Then, we propose a triad transition matrix prediction algorithm to learn the change of the distribution of triads among the different snapshots. The learned changes in the distribution of triads can capture the dynamic evolution of the network. With a proposed triad transition influence quantification algorithm, we propose a motifs based link prediction method for temporal link prediction. The proposed method can capture the dynamic evolution of temporal networks and is universal than existing methods. Extensive experiments on disparate real-world networks and model networks with controllable evolution demonstrate the effectiveness of the proposed method.

Signed network representation is a key problem for signed network data. Previous studies have shown that by preserving multi-order signed proximity (SP), expressive node representations can be learned. However, multi-order SP cannot be perfectly encoded using limited samples extracted from random walks, which reduces effectiveness. To perfectly encode multi-order SP, we have innovatively integrated the informativeness of infinite samples to construct high-level summaries of multi-order SP without explicit sampling. Based on these summaries, we propose a method called SPMF, in which node representations are obtained using low-rank matrix approximation. Furthermore, we theoretically investigate the rationality of SPMF by examining its relationship with a powerful representation learning architecture. In sign inference and link prediction tasks with several real-world datasets, SPMF is empirically competitive compared with state-of-the-art methods. Additionally, two tricks are designed for improving the scalability of SPMF. One trick aims to filter out less informative summaries, and another one is inspired by kernel techniques. Both tricks empirically improve scalability while preserving effective performance. The code for our methods is publicly available.

Signed network embedding (SNE) has received considerable attention in recent years. A mainstream idea of SNE is to learn node representations by estimating the ratio of sampling densities. Though achieving promising performance, these methods based on density ratio estimation are limited to the issues of confusing sample, expected error, and fixed priori. To alleviate the above-mentioned issues, in this paper, we propose a novel dual-branch density ratio estimation (DDRE) architecture for SNE. Specifically, DDRE 1) consists of a dual-branch network, dealing with the confusing sample; 2) proposes the expected matrix factorization without sampling to avoid the expected error; and 3) devises an adaptive cross noise sampling to alleviate the fixed priori. We perform sign prediction and node classification experiments on four real-world and three artificial datasets, respectively. Extensive empirical results demonstrate that DDRE not only significantly outperforms the methods based on density ratio estimation but also achieves competitive performance compared with other types of methods such as graph likelihood, generative adversarial networks, and graph convolutional networks. Code is publicly available at https://github.com/WHU-SNA/DDRE.

Yuren Mao, Zekai Wang, Weiwei Liu, Xuemin Lin, Wenbin Hu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Social trust network embedding is a useful way for efficient social trust network analysis. To get more expressive representations, the latent feature and node role feature should be preserved. In many cases, the dimension of latent feature can be large, thus latent feature has storage problem with the scale of networks increasing. As hash has a good performance on compressing, we use hash to reduce the memory needed for storing latent feature. Graphlets are useful statistics for modeling the node role. Overall, in this study, we propose a novel social trust network embedding method with the concepts of hash and graphlet (STNH). Neither of them has been researched for social trust networks in prior studies. We evaluate STNH on five realworld social trust networks with respect to the downstream task of link prediction. The results demonstrate the efficacy of STNH.

With the rapid development of urbanization, the problem of urban traffic congestion has become increasingly prominent. Dynamic route guidance promises to improve the capacity of urban traffic management and mitigate traffic congestion in big cities. In the design of simulation-based experiments for most dynamic route guidance methods, the simulation data is generally estimated from a specific traffic scenario in the real-world. However, highly dynamic traffic in the city implies that traffic scenarios in real systems are diverse. Therefore, if a route guidance method cannot adjust its strategy according to the spatial and temporal characteristics of different traffic scenarios, then it cannot guarantee optimal results under all traffic scenarios. Thus, ideal dynamic route guidance methods should have a highly adaptive learning ability under diverse traffic scenarios so as to have extensive improvement capabilities for different traffic scenarios. In this study, an A* trajectory rejection method based on multi-agent reinforcement learning (A*R2) is proposed; the method integrates both system and user perspectives to mitigate traffic congestion and reduce travel time (TT) and travel distance (TD). First, owing to its adaptive learning ability, the A*R2can comprehensively analyze the traffic conditions for different traffic scenarios and intelligently evaluate the road congestion index from a system perspective. Then, the A*R2determines the routes for all vehicles from user perspective according to the road network congestion index. An extensive set of simulation experiments reveal that, under various traffic scenarios, the A*R2can rely on its adaptive learning ability to achieve better traffic efficiency. Moreover, even in cases where many drivers are not fully compliant with the route guidance, the traffic efficiency can still be improved significantly by A*R2.

Temporal network embedding, which aims to learn the low-dimensional representations of nodes in temporal networks that can capture and preserve the network structure and evolution pattern, has attracted much attention from the scientific community. However, existing methods suffer from two main disadvantages: 1) they cannot preserve the node temporal proximity that capture important properties of the network structure; and 2) they cannot represent the nonlinear structure of temporal networks. In this paper, we propose a high-order nonlinear information preserving (HNIP) embedding method to address these issues. Specifically, we define three orders of temporal proximities by exploring network historical information with a time exponential decay model to quantify the temporal proximity between nodes. Then, we propose a novel deep guided auto-encoder to capture the highly nonlinear structure. Meanwhile, the training set of the guide auto-encoder is generated by the temporal random walk (TRW) algorithm. By training the proposed deep guided auto-encoder with a specific mini-batch stochastic gradient descent algorithm, HNIP can efficiently preserves the temporal proximities and highly nonlinear structure of temporal networks. Experimental results on four real-world networks demonstrate the effectiveness of the proposed method.

As communities represent similar opinions, similar functions, similar purposes, etc., community detection is an important and extremely useful tool in both scientific inquiry and data analytics. However, the classic methods of community detection, such as spectral clustering and statistical inference, are falling by the wayside as deep learning techniques demonstrate an increasing capacity to handle high-dimensional graph data with impressive performance. Thus, a survey of current progress in community detection through deep learning is timely. Structured into three broad research streams in this domain – deep neural networks, deep graph embedding, and graph neural networks, this article summarizes the contributions of the various frameworks, models, and algorithms in each stream along with the current challenges that remain unsolved and the future research opportunities yet to be explored.

Social media sites are now becoming very important platforms for product promotion or marketing campaigns. Therefore, there is broad interest in determining ways to guide a site to react more positively to a product with a limited budget. However, the practical significance of the existing studies on this subject is limited for two reasons. First, most studies have investigated the issue in oversimplified networks in which several important network characteristics are ignored. Second, the opinions of individuals are modeled as bipartite states (e.g., support or not) in numerous studies, however, this setting is too strict for many real scenarios. In this study, we focus on social trust networks (STNs), which have the significant characteristics ignored in the previous studies. We generalized a famed continuous-valued opinion dynamics model for STNs, which is more consistent with real scenarios. We subsequently formalized two novel problems for solving the issue in STNs. In addition, we developed two matrix-based methods for these two problems and experiments on realworld datasets to demonstrate the practical utility of our methods.

Trust prediction in online social networks is crucial for information dissemination, product promotion, and decision making. Existing work on trust prediction mainly utilizes the network structure or the low-rank approximation of a trust network. These approaches can suffer from the problem of data sparsity and prediction accuracy. Inspired by the homophily theory, which shows a pervasive feature of social and economic networks that trust relations tend to be developed among similar people, we propose a novel deep user model for trust prediction based on user similarity measurement. It is a comprehensive data sparsity insensitive model that combines a user review behavior and the item characteristics that this user is interested in. With this user model, we firstly generate a user's latent features mined from user review behavior and the item properties that the user cares. Then we develop a pair-wise deep neural network to further learn and represent these user features. Finally, we measure the trust relations between a pair of people by calculating the user feature vector cosine similarity. Extensive experiments are conducted on two real-world datasets, which demonstrate the superior performance of the proposed approach over the representative baseline works.

Developing effective network embedding methods for social trust networks (STNs) is a non-trivial problem because two key pieces of information need to be preserved simultaneously: a user's relations to latent factors and the trust transfer patterns that govern what type of relationship will form. In this study, we propose a novel social trust network embedding method (STNE) to address these issues. Specifically, we present a modified Skip-Gram model with negative sampling to jointly learn latent factor features, along with the trust transfer pattern features. Moreover, we define a flexible notion about a user's latent relationships with other users, which generates reliable negative samples for optimization. Extensive experiments on several real-world networks demonstrate the efficacy of the proposed STNE.

Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the structure and inherent properties of the network. Most existing network embedding methods didn't consider network noise. However, it is almost impossible to observe the actual structure of a real-world network without noise. The noise in the network will affect the performance of network embedding dramatically. In this paper, we aim to exploit node similarity to address the problem of social network embedding with noise and propose a node similarity preserving (NSP) embedding method. NSP exploits a comprehensive similarity index to quantify the authenticity of the observed network structure. Then we propose an algorithm to construct a correction matrix to reduce the influence of noise. Finally, an objective function for accurate network embedding is proposed and an efficient algorithm to solve the optimization problem is provided. Extensive experimental results on a variety of applications of real-world networks with noise show the superior performance of the proposed method over the state-of-the-art methods.

Link prediction in signed social networks is an important and challenging problem in social network analysis. To produce the most accurate prediction results, two questions must be answered: (1) Which unconnected node pairs are likely to be connected by a link in future? (2) What will the signs of the new links be? These questions are challenging, and current research seldom well solves both issues simultaneously. Additionally, neutral social relationships, which are common in many social networks can affect the accuracy of link prediction. Yet neutral links are not considered in most existing methods. Hence, in this paper, we propose a s igned l atent f actor (SLF) model that answers both these questions and, additionally, considers four types of relationships: positive, negative, neutral and no relationship at all. The model links social relationships of different types to the comprehensive, but opposite, effects of positive and negative SLFs. The SLF vectors for each node are learned by minimizing a negative log-likelihood objective function. Experiments on four real-world signed social networks support the efficacy of the proposed model.

Based on the performance of entire social networks, anomaly analysis for evolving social networks generally ignores the otherness of the evolutionary behaviors of different nodes, such that it is difficult to precisely identify the anomalous evolutionary behaviors of nodes ( AEBN ). Assuming that a node's evolutionary behavior that generates and removes edges normally follows stable evolutionary mechanisms, this study focuses on detecting and assessing AEBN, whose evolutionary mechanisms deviate from their past mechanisms, and proposes a link prediction detection ( LPD ) method and a matrix perturbation assessment ( MPA ) method. LPD describes a node's evolutionary behavior by fitting its evolutionary mechanism, and designs indexes for edge generation and removal to evaluate the extent to which the evolutionary mechanism of a node's evolutionary behavior can be fitted by a link prediction algorithm. Furthermore, it detects AEBN by quantifying the differences among behavior vectors that characterize the node's evolutionary behaviors in different periods. In addition, MPA considers AEBN as a perturbation of the social network structure, and quantifies the effect of AEBN on the social network structure based on matrix perturbation analysis. Extensive experiments on eight disparate real-world networks demonstrate that analyzing AEBN from the perspective of evolutionary mechanisms is important and beneficial.

Matrix Factorization based methods, e.g., the Concept Factorization (CF) and Nonnegative Matrix Factorization (NMF), have been proved to be efficient and effective for data clustering tasks. In recent years, various graph extensions of CF and NMF have been proposed to explore intrinsic geometrical structure of data for the purpose of better clustering performance. However, many methods build the affinity matrix used in the manifold structure directly based on the input data. Therefore, the clustering results are highly sensitive to the input data. To further improve the clustering performance, we propose a novel manifold concept factorization model with adaptive neighbor structure to learn a better affinity matrix and clustering indicator matrix at the same time. Technically, the proposed model constructs the affinity matrix by assigning the adaptive and optimal neighbors to each point based on the local distance of the learned new representation of the original data with itself as a dictionary. Our experimental results present superior performance over the state-of-the-art alternatives on numerous datasets.

Wireless on-demand data broadcasting (ODDB) has become the preferred method of disseminating data to a large number of mobile users. The rapid boom in client requests has resulted in an urgent demand for improved ODDB system capacity (number of service users), especially in client-intensive and request-frequent environments. There are two bottlenecks in ODDB systems: the base station access capacity and the server concurrency capability. However, existing algorithms do not consider these bottlenecks, leading to deficient performance in ODDB system capacity and broadcast efficiency. In this paper, a three-layer ODDB system architecture and a request pre-processing method (RPPM) are proposed. The innovations of this study are twofold: (1) The three-layer ODDB system architecture enhances the base station access capacity by introducing a virtual node layer to share the high load of the base station. (2) Based on the proposed architecture, the RPPM handles request merger and priority evaluation to reduce server concurrency and improve broadcast efficiency. The results of experiments and analyses reveal that the proposed method can significantly enhance the ODDB system capacity and obtain outstanding broadcast efficiency.

Recently, social networks have witnessed a massive surge in popularity. A key issue in social network research is network evolution analysis, which assumes that all the autonomous nodes in a social network follow uniform evolution mechanisms. However, different nodes in a social network should have different evolution mechanisms to generate different edges. This is proposed as the underlying idea to ensure the nodes' evolution diversity in this paper. Our approach involves identifying the micro-level node evolution that generates different edges by introducing the existing link prediction methods from the perspectives of nodes. We also propose the edge generation coefficient to evaluate the extent to which an edge's generation can be explained by a link prediction method. To quantify the nodes' evolution diversity, we define the diverse evolution distance. Furthermore, a diverse node adaption algorithm is proposed to indirectly analyze the evolution of the entire network based on the nodes' evolution diversity. Extensive experiments on disparate real-world networks demonstrate that the introduction of the nodes' evolution diversity is important and beneficial for analyzing the network evolution. The diverse node adaption algorithm outperforms other state-of-the-art link prediction algorithms in terms of both accuracy and universality. The greater the nodes' evolution diversity, the more obvious its advantages.

Accurate short-term flow forecasting is important for the real-time traffic control, but due to its complex nonlinear data pattern, getting a high precision is difficult. The support vector regression model (SVR) has been widely used to solve nonlinear regression and time series predicting problems. This paper presents a Hybrid PSO-SVR forecasting method to get a higher precision with less learning time; this method uses Particle Swarm Optimization (PSO) to search optimal SVR parameters. And to find a PSO that is more proper to SVR parameters searching, this paper proposes three kinds of strategies to handle the particles flow out the searching space, according to comparison, one of the strategies can make PSO get the optimal parameters more quickly, this paper calls the PSO using this strategy as fast PSO. Furthermore, to handle the precision's decline caused by the noises in the original data, this paper proposes a hybrid PSO-SVR method with historical momentum based on the similarity of historical short-term flow data. The forecasting results of extensive comparison experiments indicate that proposed model can get more accurate forecasting result than other state-of-the-art algorithms; and when the data containing noises, the method with historical momentum still deserves accurate forecasting.

Abstract On‐demand data broadcasting scheduling is an effective wireless data dissemination technique. Existing scheduling algorithms usually have two problems: (1) with the explosive growth of mobile users and real‐time individual requirements, broadcasting systems present a shortage of scalability, dynamics and timeliness (request drop ratio); (2) with the growth of intelligent and entertained application, energy consumption of mobile client cannot be persistent (tuning time). This paper proposes an effective scheduling algorithm LxRxW. It takes into account the number of lost requests during next item broadcasting time, the number of requests and the waiting time. LxRxW can reduce the request drop ratio. At the same time, the algorithm employs a dynamic index strategy to put forward a dynamic adjusting method on the index cycle length (DAIL) to determine the proper index cycle. Extensive experimental results show that the LxRxW algorithm has better performance than other state‐of‐the‐art scheduling algorithms and can significantly reduce the drop ratio of user requests by 40%–50%. The request drop ratio and accessing time of LxRxW with index increase by 1%–2% than LxRxW algorithm without index, but the tuning time decreases by 70%. The index strategy shows that when the index cycle length is less than 20units, it can significantly reduce the average tuning time but when the index cycle length continues increasing, the average tuning time will increase contrarily. DAIL can dynamically determine the length of index cycle. Moreover, it can reach optimal integrated performance of the request drop ratio, the average accessing time and the average tuning time. Copyright © 2013 John Wiley & Sons, Ltd.