no code implementations • 27 May 2024 • Xinyi Gao, Tong Chen, Wentao Zhang, Yayong Li, Xiangguo Sun, Hongzhi Yin
Consequently, due to the limited generalization capacity of condensed graphs, applications that employ GC for efficient GNN training end up with sub-optimal GNNs when confronted with evolving graph structures and distributions in dynamic real-world situations.
no code implementations • 20 Jan 2022 • Yayong Li, Jie Yin, Ling Chen
It aims to augment the training set with pseudo-labeled unlabeled nodes with high confidence so as to re-train a supervised model in a self-training cycle.
no code implementations • 5 Mar 2021 • Yayong Li, Jie Yin, Ling Chen
Learning with label noise has been primarily studied in the context of image classification, but these techniques cannot be directly applied to graph-structured data, due to two major challenges -- label sparsity and label dependency -- faced by learning on graphs.
no code implementations • ICLR 2022 • Wei Huang, Yayong Li, Weitao Du, Jie Yin, Richard Yi Da Xu, Ling Chen, Miao Zhang
Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally.
no code implementations • 22 Aug 2019 • Yayong Li, Jie Yin, Ling Chen
In this paper, we propose a SEmi-supervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy in an adversarial way.