Collaborative and Efficient Fine-tuning: Leveraging Task Similarity

2026-02-06

AI Summary

This work addresses the challenge of fine-tuning foundation models in data-scarce scenarios by proposing CoLoRA, a collaborative low-rank adaptation method. CoLoRA introduces task similarity into parameter-efficient fine-tuning for the first time, establishing a dual-branch architecture comprising shared and task-specific adapters that operate in synergy. Through multi-task joint training, the framework enables effective knowledge transfer across related tasks. Theoretical analysis provides provable guarantees for parameter recovery in heterogeneous linear regression settings. Experimental results on natural language tasks demonstrate that co-training with similar tasks significantly enhances performance across all tasks, effectively mitigating data scarcity and improving fine-tuning efficacy.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Game Theory and Economic Paradigms: Adversarial Learning
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Adaptability has been regarded as a central feature in the foundation models, enabling them to effectively acclimate to unseen downstream tasks. Parameter-efficient fine-tuning methods such as celebrated LoRA facilitate efficient adaptation of large foundation models using labeled, high-quality and generally scarce task data. To mitigate data scarcity in fine-tuning of foundation models, we propose to leverage task similarity across multiple downstream users. Intuitively, users with similar tasks must be able to assist each other in boosting the effective fine-tuning data size. We propose Collaborative Low-Rank Adaptation, or CoLoRA, which exploits task similarity to collaboratively and efficiently fine-tune personalized foundation models. The main idea in CoLoRA is to train one shared adapter capturing underlying task similarities across all tasks, and personalized adapters tailored to user-specific tasks. We theoretically study CoLoRA on heterogeneous linear regression and provide provable guarantees for ground truth recovery. We also conduct several natural language experiments with varying task similarity, which further demonstrate that when trained together with similar tasks, individual performances are significantly boosted.

Problem

• data scarcity
• fine-tuning
• task similarity
• foundation models
• parameter-efficient adaptation

Innovation

• Collaborative Fine-tuning
• Task Similarity
• Parameter-Efficient Adaptation
• Low-Rank Adaptation
• Foundation Models