7 papers
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions
Wenhao Zhang, Lin Mu, Li Ni +2
Low-rank adaptation (LoRA) is a widely used strategy for efficient fine-tuning of large language models (LLMs), but its strictly linear structure fundamentally limits expressive ca…
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models
Lin Mu, Haiyang Wang, Li Ni +4
Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions further enhance flexibility by dy…
From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation
Ziang Lu, Lei Sang, Lin Mu +1
Cross-domain Recommendation (CDR) exploits multi-domain correlations to alleviate data sparsity. As a core task within this field, inter-domain recommendation focuses on predicting…
Pre-trained Prompt-driven Semi-supervised Local Community Detection
Li Ni, Hengkai Xu, Lin Mu +2
Semi-supervised local community detection aims to leverage known communities to detect the community containing a given node. Although existing semi-supervised local community dete…
DenseLoRA: Dense Low-Rank Adaptation of Large Language Models
Lin Mu, Xiaoyu Wang, Li Ni +4
Low-rank adaptation (LoRA) has been developed as an efficient approach for adapting large language models (LLMs) by fine-tuning two low-rank matrices, thereby reducing the number o…
Community Search in Time-dependent Road-social Attributed Networks
Li Ni, Hengkai Xu, Lin Mu +2
Real-world networks often involve both keywords and locations, along with travel time variations between locations due to traffic conditions. However, most existing cohesive subgra…