12 papers
TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
Xiaosong Han, Ke Chen, Xindi Dai +7
In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. Ho…
Advancing Graph Few-Shot Learning via In-Context Learning
Renchu Guan, Yajun Wang, Chunli Guo +5
Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning. However, existing methods…
KoRe: Compact Knowledge Representations for Large Language Models
Davide Cavicchini, Fausto Giunchiglia, Jacopo Staiano
Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvements in reasoning capabilities…
Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion
Yonghao Liu, Jialu Sun, Wei Pang +4
Graph few-shot learning, which focuses on effectively learning from only a small number of labeled nodes to quickly adapt to new tasks, has garnered significant research attention.…
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…
Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs
Renchu Guan, Xuyang Li, Yachao Zhang +5
Hypergraphs, as a generalization of traditional graphs, naturally capture high-order relationships. In recent years, hypergraph neural networks (HNNs) have been widely used to capt…