4 papers
Community-Aware Temporal Walks: Parameter-Free Representation Learning on Continuous-Time Dynamic Graphs
He Yu, Jing Liu
Dynamic graph representation learning plays a crucial role in understanding evolving behaviors. However, existing methods often struggle with flexibility, adaptability, and the pre…
Two Layer Walk: A Community-Aware Graph Embedding
He Yu, Jing Liu
Community structures are critical for understanding the mesoscopic organization of networks, bridging local and global patterns. While methods such as DeepWalk and node2vec capture…
Deep Insights into Automated Optimization with Large Language Models and Evolutionary Algorithms
He Yu, Jing Liu
Designing optimization approaches, whether heuristic or meta-heuristic, usually demands extensive manual intervention and has difficulty generalizing across diverse problem domains…
AutoRNet: Automatically Optimizing Heuristics for Robust Network Design via Large Language Models
He Yu, Jing Liu
Achieving robust networks is a challenging problem due to its NP-hard nature and complex solution space. Current methods, from handcrafted feature extraction to deep learning, have…