Yuan Li

Dynamic Fusion of Topology and History: The AdaGPS Architecture with GatEdgeformer

Graph Transformers show immense potential in graph representation learning, yet adaptively capturing complex topological dependencies remains a critical challenge. This paper proposes AdaGPS, a novel adaptive architecture featuring three core improvements. First, the introduced GatEdgeformer module injects edge feature...

CCEC-TGN for Link Prediction in Large-Scale Continuous-Time Dynamic Graphs

Temporal link prediction aims to forecast future connections from historical interactions. As a fundamental problem in temporal graph learning, existing methods exhibit three major limitations. (1) They usually focus on node-level interaction histories and information aggregated from temporal neighbors, while overlooki...

Beyond Locality: Multi-scale Structural Tokenization for Unsupervised Community Search

Community Search (CS) aims to retrieve query-dependent cohesive subgraphs from networks, playing a crucial role in modern applications such as computing power networks and biological systems. Given the high cost of labeling, unsupervised CS has emerged as a scalable paradigm. However, existing approaches often suffer f...

CodeSeed: An Evidence-Verified Agent with Bounded Reflection for Algorithm Learning Archives