5 papers
Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification
Mengyu Li, Yonghao Liu, Fausto Giunchiglia +3
Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the…
Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks
Yonghao Liu, Mengyu Li, Fausto Giunchiglia +4
Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it.Current leading graph model…
Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning
Yonghao Liu, Mengyu Li, Wei Pang +4
Short text classification, as a research subtopic in natural language processing, is more challenging due to its semantic sparsity and insufficient labeled samples in practical sce…
Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training
Yonghao Liu, Mengyu Li, Ximing Li +5
Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies hav…
Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference
Yonghao Liu, Mengyu Li, Di Liang +5
Natural Language Inference (NLI) is a crucial task in natural language processing that involves determining the relationship between two sentences, typically referred to as the pre…