Pengzhi Chu — accepted AI-conference papers

2024

Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases

Hang Yin, Liyao Xiang, Dong Ding, Yuheng He, Yihan Wu, Pengzhi Chu +2

NeurIPS 2024poster

We investigate the entity alignment (EA) problem with unlabeled dangling cases, meaning that partial entities have no counterparts in the other knowledge graph (KG), yet these entities are unlabeled. The problem arises when the source and target graphs are of different scales, and it is much cheaper…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

Permutation Equivariance of Transformers and Its Applications

Hengyuan Xu, Liyao Xiang, Hangyu Ye, Dixi Yao, Pengzhi Chu, Baochun Li

CVPR 2024poster

Revolutionizing the field of deep learning Transformer-based models have achieved remarkable performance in many tasks. Recent research has recognized these models are robust to shuffling but are limited to inter-token permutation in the forward propagation. In this work we propose our definition of…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗