Shirui Pan

Low-Rank and Sparse Matrix Factorization for Scientific Paper Recommendation in Heterogeneous Network

2018 · IEEE Access

With the rapid growth of scientific publications, it is hard for researchers to acquire appropriate papers that meet their expectations. Recommendation system for scientific articles is an essential technology to overcome this problem. In this …

Heterogeneous Information Network Embedding based Personalized Query-Focused Astronomy Reference Paper Recommendation

2018 · International Journal of Computational Intelligence Systems

Fast-growing scientific papers bring the problem of rapidly and accurately finding a list of reference papers for a given manuscript. Reference paper recommendation is an essential technology to overcome this obstacle. In this paper, we …

FraudNE: a Joint Embedding Approach for Fraud Detection

2018

Detecting fraudsters is a meaningful problem for both users and e-commerce platform. Existing graph-based approaches mainly adopt shallow models, which cannot capture the highly non-linear relationship between vertexes in a bipartite graph composed of users …

Long-short Distance Aggregation Networks for Positive Unlabeled Graph Learning

2019

Graph neural nets are emerging tools to represent network nodes for classification. However, existing approaches typically suffer from two limitations: (1) they only aggregate information from short distance (e.g., 1-hop neighbors) each round and fail …

Unsupervised Domain Adaptive Graph Convolutional Networks

2020

Graph convolutional networks (GCNs) have achieved impressive success in many graph related analytics tasks. However, most GCNs only work in a single domain (graph) incapable of transferring knowledge from/to other domains (graphs), due to the …

Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization

2020

One-Shot Neural Architecture Search (NAS) significantly improves the computational efficiency through weight sharing. However, this approach also introduces multi-model forgetting during the supernet training (architecture search phase), where the performance of previous architectures degrade when …

Multivariate Relations Aggregation Learning in Social Networks

2020

Multivariate relations are general in various types of networks, such as biological networks, social networks, transportation networks, and academic networks. Due to the principle of ternary closures and the trend of group formation, the multivariate …

Model Extraction Attacks on Graph Neural Networks

2022 · Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security

Machine learning models are shown to face a severe threat from Model Extraction Attacks, where a well-trained private model owned by a service provider can be stolen by an attacker pretending as a client. Unfortunately, …

Projective Ranking-based GNN Evasion Attacks

2022 · IEEE Transactions on Knowledge and Data Engineering

Graph neural networks (GNNs) offer promising learning methods for graph-related tasks. However, GNNs are at risk of adversarial attacks. Two primary limitations of the current evasion attack methods are highlighted: (1) The currentGradArgmaxignores the “long-term” …

BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks

2026

Rui Miao, Yixin Liu, Yili Wang, Xu Shen, Yue Tan, Yiwei Dai, Shirui Pan, Xin Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable …

Unifying Large Language Models and Knowledge Graphs: A Roadmap

2024 · IEEE Transactions on Knowledge and Data Engineering

Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, …