arXiv Machine Learning By Yan Wang, Chuan-Xian Ren

Pair-Centric Graph Rewiring for Over-Squashing via Optimal Transport-Guided Communication Alignment

Read the original on arXiv Machine Learning →

arXiv:2608. 10619v1 Announce Type: new Abstract: Message-passing neural networks (MPNNs) often struggle when task-relevant information is distributed across distant regions of a graph, since local propagation must compress remote signals through limited structural interfaces.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
5d ago

SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization

arXiv:2608. 12443v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a co-sampled solution group.

By Yuanyu Li, Jintao Xu, Zijiang Liu, Yongzhi Qi, Ningxuan Kang, Jianshen Zhang, Wei Qi, Chen Xie, Zuo-Jun Max Shen
arXiv Machine Learning
Jul 31

Schreier-Coset Graph Rewiring

arXiv:2607. 27479v1 Announce Type: new Abstract: The information flow in the graph neural networks (GNNs) is fundamentally constrained by over-squashing, where structural bottlenecks impede long range information propagation.

By Aryan Mishra, Randy Martinez, Lizhen Lin