Researcher — paper.dinq.me

2026 顶会论文

作者位次 #6/9ICLR 2026Poster· Deep Learning / Graph Neural Networks

Paradigm Shift of GNN Explainer from Label Space to Prototypical Representation Space

Jun Yin · Senzhang Wang · Ziluowen Luo · Peng Huo · Hao Yan · Hao Miao · Chaozhuo Li · Shirui Pan · Chengqi Zhang

可解释性OpenReview

作者位次 #4/6ICLR 2026Poster· Applications / Time Series

ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting

Jindong Tian · Yifei Ding · Ronghui Xu · Hao Miao · Guo · Bin Yang

OpenReview

作者位次 #4/6SIGIR 2026Oral· Information Retrieval (Full)

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning

Xiangmeng Wang · Qian Li · Haiyang Xia · Hao Miao · Li Qing · Guandong Xu

摘要

Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-local neighbor extension or architecture refinement. However, the fundamental...

推理效率与系统数据与预训练OpenReview

作者位次 #3/6KDD 2026Oral· Knowledge Discovery & Data Mining