Author name cluster

Shaolin Tan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

AAAI Conference 2026 Conference Paper

Subgraph Encoding with Bicentric Sphere Node Labeling and Pooling for Link Prediction

Zhihong Fang
Shaolin Tan
Qiu Fang
Zhe Li
Qing Gao

Learning representation of the enclosing subgraph of node pairs is recognized as an efficient approach for link-oriented prediction tasks in network applications. The core challenge within this subgraph encoding approach is how to effectively distinguish and then properly aggregate the contribution of nodes in the subgraph into a single vector to indicate the relation between the target node pair. In this work, we propose a novel sphere-based subgraph encoding architecture, namely BS-SubGNN, to address the challenge. In detail, we design two key building blocks, including Bicentric Sphere Node Labeling (BSNL) and Bicentric Sphere Subgraph Pooling (BSSP) to assist message passing in BS-SubGNN. BSNL endows each node a label according to the sphere it belongs to in the subgraph to distinguish the contribution of nodes, while BSSP adopts an attention mechanism to aggregate the contribution of nodes in each sphere. Theoretically, we prove that BS-SubGNN can unify existing node distance labeling methods, and yield discriminative node features with less time complexity. We evaluate the performance of BS-SubGNN in link prediction tasks over a variety of network types, including undirected networks, attribute networks, directed networks, and signed directed networks. Our experimental results demonstrate that BS-SubGNN consistently achieves significant performance improvements over the above diverse types of networks. In particular, compared to those methods with a requisite of multi-hop neighborhood information, BS-SubGNN can obtain better performance even when only one-hop neighborhood information of the node pair is utilized.

PDF Details DOI

EAAI Journal 2025 Journal Article

Backtracing Byzantine attacks in distributed average consensus networks: A gated graph neural network approach with graph reconstruction

Xinliang Wang
Shaolin Tan
Ye Tao
Nian Liu
Bing Li
Suixiang Gao

Byzantine attackers disguise themselves as normal nodes yet propagate incorrect information in the network to disrupt the function of distributed systems. Current Byzantine detecting approaches commonly rely on the delivered data among agents, where an agent is supposed to be a Byzantine attacker if its delivered data significantly differs with others. In this paper, for the first time we suppose that the transmission data within the network is not known due to privacy consideration and propose the problem of backtracing Byzantine attackers through observed states. To address this problem, we adopt the idea of backtracing patient in disease spreading networks and propose a gated graph neural network with graph reconstruction to effectively localize the Byzantine attackers in multi-agent networks. This approach first develops a data-driven method to learn the networking structure of the multi-agent systems and then builds a gated graph neural network based on the reconstructed graph to classify the nodes into normal ones and Byzantine ones. Compared with previous Byzantine detecting methods, the proposed approach is fully driven by the measured output state of each agent and localizes the attacker from external perspective. Extensive experimental results are conducted to confirm that the proposed Byzantine attack detector performs well across various testing parameters.

Details DOI

ECAI Conference 2025 Conference Paper

Safe APG: Accelerated Policy Gradient Algorithm for Secure Policy Updating in Reinforcement Learning

Jianan Lin
Yao Chen 0003
Zhengyang Ji
Yuan Meng
Bo Hou
Shaolin Tan

Inverse reinforcement learning (IRL) aims to infer the reward function from expert demonstrations. However, as IRL techniques are increasingly applied in high-stakes domains such as autonomous driving and military decision-making, reward function leakage has emerged as a critical risk, potentially leading to severe security threats and unintended consequences. To address this challenge, we propose Safe Accelerated Policy Gradient (Safe APG), a method designed to enhance learning security of the demonstrating agent by preventing observers from inferring its reward function. The core idea behind Safe APG is to incorporate a delicately constructed and theoretically guaranteed structural noise into Nesterov’s Accelerated Gradient (NAG) for policy updating, with the goal of concealing critical gradient information from the learning agent as well as keeping the geometric convergence property of NAG. The results from numerical experiments and simulations in reinforcement learning environments demonstrate that the proposed method not only significantly mitigates reward function leakage, but also achieves superior convergence rates even under the perturbation of the introduced structural noise.

Details