8 citations · 27 across the 5 of their papers we have counts for
5 papers
Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network
Yilun Zheng, Jiahao Xu, Lihui Chen
Under circumstances of heterophily, where nodes with different labels tend to be connected based on semantic meanings, Graph Neural Networks (GNNs) often exhibit suboptimal perform…
DistillCSE: Distilled Contrastive Learning for Sentence Embeddings
Jiahao Xu, Wei Shao, Lihui Chen +1
This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCS…
On Synthetic Data for Back Translation
Jiahao Xu, Yubin Ruan, Wei Bi +4
Back translation (BT) is one of the most significant technologies in NMT research fields. Existing attempts on BT share a common characteristic: they employ either beam search or r…
SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives
Jiahao Xu, Wei Shao, Lihui Chen +1
This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspe…
LA-HCN: Label-based Attention for Hierarchical Multi-label TextClassification Neural Network
Xinyi Zhang, Jiahao Xu, Charlie Soh +1
Hierarchical multi-label text classification (HMTC) has been gaining popularity in recent years thanks to its applicability to a plethora of real-world applications. The existing H…