{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/r-lora-random-initialization-of-multi-head","title":"R-LoRA: Random Initialization of Multi-Head LoRA for Multi-Task Learning","arxiv_id":"2502.15455","date":"2025-02-21","proceeding":null,"authors":["Jinda Liu","Yi Chang","Yuan Wu"],"abstract":"Fine-tuning large language models (LLMs) is prohibitively expensive in terms of computational and memory costs. Low-rank Adaptation (LoRA), as one of the most popular parameter-efficient fine-tuning (PEFT) methods, offers a cost-effective alternative by approximating the model changes $\\Delta W \\in \\mathbb{R}^{m \\times n}$ through the product of down-projection matrix $A \\in \\mathbb{R}^{m \\times r}$ and head matrix $B \\in \\mathbb{R}^{r \\times n}$, where $r \\ll \\min(m, n)$. In real-world scenarios, LLMs are fine-tuned on data from multiple domains to perform tasks across various fields, embodying multi-task learning (MTL). LoRA often underperforms in such complex scenarios. To enhance LoRA's capability in multi-task learning, we propose R-LoRA, which incorporates Multi-Head Randomization. Multi-Head Randomization diversifies the head matrices through Multi-Head Random Initialization and Multi-Head Dropout, enabling more efficient learning of task-specific features while maintaining shared knowledge representation. Extensive experiments demonstrate that R-LoRA is better at capturing task-specific knowledge, thereby improving performance in multi-task scenarios. The code is available at https://github.com/jinda-liu/R-LoRA.","url_abs":"https://arxiv.org/abs/2502.15455v1","url_pdf":"https://arxiv.org/pdf/2502.15455v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"r-lora-random-initialization-of-multi-head","repo_url":"https://github.com/jinda-liu/r-lora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.15455","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}