Research map / Label-efficient and robust learning / Recognition and long-tail
Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
Gagik Magakyan, Amirhossein Reisizadeh, Chanwoo Park, Pablo A. Parrilo, Asuman E. Ozdaglar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train collaboratively with CoLoRA instead of local LoRA | Qwen2.5-1.5B-Instruct · task group, similarity 0.265 | RougeL: 0.910 -> 0.970 | Improved |
| train collaboratively with CoLoRA instead of local LoRA | Qwen2.5-1.5B-Instruct · task group, similarity 0.193 | RougeL: 0.937 -> 0.948 | Improved |
| train collaboratively with CoLoRA instead of local LoRA | Qwen2.5-1.5B-Instruct · task group, similarity 0.114 | RougeL: 0.405 -> 0.378 | Hurt |
| train collaboratively with CoLoRA instead of local LoRA | Qwen2.5-1.5B-Instruct · task group, similarity 0.234 | RougeL: 0.635 -> 0.727 | Improved |
| train collaboratively with CoLoRA instead of local LoRA | Qwen2.5-1.5B-Instruct · task group, similarity 0.222 | RougeL: 0.527 -> 0.633 | Improved |
| train collaboratively with CoLoRA instead of local LoRA | Qwen2.5-1.5B-Instruct · task group, similarity 0.211 | RougeL: 0.742 -> 0.733 | Hurt |
| use CoLoRA instead of RAVAN at rank 16 | Qwen2.5-1.5B-Instruct · similarity 0.193 | RougeL: 0.813 -> 0.979 | Improved |
| use CoLoRA instead of ALoRA at rank 16 | Qwen2.5-1.5B-Instruct · similarity 0.265 | RougeL: 0.970 -> 0.960 | Hurt |
Closest papers by meaning
- Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning (ICLR 2024 · similarity 0.87)
- CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning (NeurIPS 2024 · similarity 0.87)
- FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts (NeurIPS 2025 · similarity 0.86)
- Measuring Task Similarity and Its Implication in Fine-Tuning Graph Neural Networks (AAAI 2024 · similarity 0.86)
- Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation (NeurIPS 2024 · similarity 0.86)
- PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
