Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleOctober 2024
Deeply Fusing Semantics and Interactions for Item Representation Learning via Topology-driven Pre-training
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 9505–9514https://doi.org/10.1145/3664647.3681639Learning item representation is crucial for a myriad of on-line e-commerce applications. The nucleus of retail item representation learning is how to properly fuse the semantics within a single item, and the interactions across different items generated ...
- research-articleOctober 2024
Information Diffusion Prediction with Graph Neural Ordinary Differential Equation Network
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 9699–9708https://doi.org/10.1145/3664647.3681363Information diffusion prediction aims to forecast the path of information spreading in social networks by exploiting user correlations or preferences. Recent works focus on characterizing the dynamic of user preferences and propose to capture users' ...
- research-articleOctober 2024
TrGa: Reconsidering the Application of Graph Neural Networks in Two-View Correspondence Pruning
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 5633–5642https://doi.org/10.1145/3664647.3681139Two-view correspondence pruning aims to accurately remove incorrect correspondences (outliers) from initial ones. Graph Neural Networks (GNNs) incorporated by Multilayer Perceptrons (MLPs) are treated as a powerful manner to handle sparse and unevenly ...
- research-articleOctober 2024
DiffGlue: Diffusion-Aided Image Feature Matching
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 8451–8460https://doi.org/10.1145/3664647.3681069As one of the most fundamental computer vision problems, image feature matching aims to establish correct correspondences between two-view images. Existing studies enhance the descriptions of feature points with graph neural network (GNN), identifying ...
- research-articleOctober 2024
CAPNet: Cartoon Animal Parsing with Spatial Learning and Structural Modeling
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 9809–9817https://doi.org/10.1145/3664647.3680570Cartoon animal parsing aims to segment the body parts such as heads, arms, legs and tails of cartoon animals. Different from previous parsing tasks, cartoon animal parsing faces new challenges, including irregular body structures, abstract drawing styles ...
-
- research-articleOctober 2024
A Source Code Vulnerability Detection Method Based on Adaptive Graph Neural Networks
ASEW '24: Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering WorkshopsPages 187–196https://doi.org/10.1145/3691621.3694950This paper proposes a mobile application vulnerability detection method based on Code Property Graphs (CPG) and adaptive graph neural networks. The method first converts source code into CPGs, then uses CodeBERT to vectorize CPG nodes. Subsequently, high-...
- research-articleOctober 2024
RCFG2Vec: Considering Long-Distance Dependency for Binary Code Similarity Detection
ASE '24: Proceedings of the 39th IEEE/ACM International Conference on Automated Software EngineeringPages 770–782https://doi.org/10.1145/3691620.3695070Binary code similarity detection(BCSD), as a fundamental technique in software security, has various applications, including malware family detection, known vulnerability detection and code plagiarism detection. Recent deep learning-based BCSD approaches ...
Detect Hidden Dependency to Untangle Commits
ASE '24: Proceedings of the 39th IEEE/ACM International Conference on Automated Software EngineeringPages 179–190https://doi.org/10.1145/3691620.3694996In collaborative software development, developers generally make code changes and commit the changes to the repositories. Among others, "making small, single-purpose commits" is considered the best practice for making commits, allowing the team to ...
- research-articleOctober 2024
GPP: A Graph-Powered Prioritizer for Code Review Requests
ASE '24: Proceedings of the 39th IEEE/ACM International Conference on Automated Software EngineeringPages 104–116https://doi.org/10.1145/3691620.3694990Peer code review has become a must-have in modern software development. However, many code review requests (CRRs) could be a backlog for large-scale and active projects, blocking continuous integration and continuous delivery (CI/CD). Prioritizing CRRs ...
- research-articleOctober 2024
GLaD: Synergizing Molecular Graphs and Language Descriptors for Enhanced Power Conversion Efficiency Prediction in Organic Photovoltaic Devices
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 4777–4785https://doi.org/10.1145/3627673.3680103This paper presents a novel approach for predicting Power Conversion Efficiency (PCE) of Organic Photovoltaic (OPV) devices, called GLaD: synergizing molecular Graphs and Language Descriptors for enhanced PCE prediction. Due to the lack of high-quality ...
- short-paperOctober 2024
Robust Heterophily Graph Learning via Uniformity Augmentation
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 4193–4197https://doi.org/10.1145/3627673.3679991Graphs serve as fundamental representations for a diverse array of complex systems, capturing intricate relationships and interactions between entities. In many real-world scenarios, graphs exhibit non-homophilous, or heterophilous, characteristics, ...
- short-paperOctober 2024
LEX-GNN: Label-Exploring Graph Neural Network for Accurate Fraud Detection
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 3802–3806https://doi.org/10.1145/3627673.3679956Graph-based fraud detection faces significant challenges, such as severe class imbalance, inconsistent connections due to the scarcity of fraudulent nodes, and the camouflage of these nodes appearing like benign nodes. Existing studies often adopt the ...
- short-paperOctober 2024
GraphVAE: Unveiling Dynamic Stock Relationships with Variational Autoencoder-based Factor Modeling
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 3807–3811https://doi.org/10.1145/3627673.3679935Factor models, originating in finance for asset pricing, are fundamental tools in quantitative investment. Recently, there has been a trend towards adopting more flexible machine learning approaches instead of previous linear models. However, traditional ...
- short-paperOctober 2024
Exploring High-Order User Preference with Knowledge Graph for Recommendation
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 4138–4142https://doi.org/10.1145/3627673.3679921Knowledge Graph (KG) has proven its effectiveness in recommendation systems. Recent knowledge-aware recommendation methods, which utilize graph neural networks and contrastive learning, underestimate two issues: 1) The neglect of modeling the latent ...
- short-paperOctober 2024
Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 4273–4277https://doi.org/10.1145/3627673.3679919With the rapid development of social media, the wide dissemination of fake news on social media is increasingly threatening both individuals and society. One of the unique challenges for fake news detection on social media is how to detect fake news on ...
- short-paperOctober 2024
A Structural Information Guided Hierarchical Reconstruction for Graph Anomaly Detection
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 4318–4323https://doi.org/10.1145/3627673.3679869Anomalies in graphs involve attributes and structures and may occur at different levels (e.g., node or community). Existing GNN-based detection methods often merely focus on anomalies of single nodes or neighborhoods, making it hard to cope with complex ...
- research-articleOctober 2024
Collaborative Fraud Detection on Large Scale Graph Using Secure Multi-Party Computation
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 1473–1482https://doi.org/10.1145/3627673.3679863Enabling various parties to share data enhances online fraud detection capabilities considering fraudsters tend to reuse resources attacking multiple platforms. Multi-party computation (MPC) techniques, such as secret sharing, offer potential privacy-...
- research-articleOctober 2024
PROSPECT: Learn MLPs on Graphs Robust against Adversarial Structure Attacks
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 425–435https://doi.org/10.1145/3627673.3679857Current adversarial defense methods for GNNs exhibit critical limitations obstructing real-world application: 1) inadequate adaptability to graph heterophily, 2) absent generalizability to early GNNs like GraphSAGE used downstream, and 3) low inference ...
- research-articleOctober 2024
NeutronCache: An Efficient Cache-Enhanced Distributed Graph Neural Network Training System
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 3310–3319https://doi.org/10.1145/3627673.3679815As real-world graph data continues to grow larger and larger, training large graphs in a distributed environment is becoming increasingly prevalent. However, network transmission in a distributed environment can hinder subsequent training steps, ...
- research-articleOctober 2024
Graph Local Homophily Network for Anomaly Detection
CIKM '24: Proceedings of the 33rd ACM International Conference on Information and Knowledge ManagementPages 706–716https://doi.org/10.1145/3627673.3679785In graph anomaly detection (GAD), the fact that anomalous nodes usually exhibit high heterophily, while most Graph Neural Networks (GNNs) have homophily assumptions, leads to poor performance. Many studies have attempted to solve this problem by ...