How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging

• URL: http://arxiv.org/abs/2412.08147v1
• Date: Wed, 11 Dec 2024 07:06:36 GMT
• Title: How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging
• Authors: Hugo Monzón Maldonado, Thomas Möllenhoff, Nico Daheim, Iryna Gurevych, Mohammad Emtiyaz Khan,
• Abstract summary: We propose to aid the search with fast previews to get a rough idea of different reweighting options.<n>We use model merging to create previews by simply reusing and averaging parameters of models trained on each task separately.
• Score: 58.61029168477524
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When finetuning multiple tasks altogether, it is important to carefully weigh them to get a good performance, but searching for good weights can be difficult and costly. Here, we propose to aid the search with fast previews to quickly get a rough idea of different reweighting options. We use model merging to create previews by simply reusing and averaging parameters of models trained on each task separately (no retraining required). To improve the quality of previews, we propose a Bayesian approach to design new merging strategies by using more flexible posteriors. We validate our findings on vision and natural-language transformers. Our work shows the benefits of model merging via Bayes to improve multitask finetuning.

Related papers

• Visual Tuning [143.43997336384126]
  Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. Recent advances can achieve superior performance than full-tuning the whole pre-trained parameters. This survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of work and models.
  arXiv  Detail & Related papers  (2023-05-10T11:26:36Z)
• Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation [53.835365470800916]
  We show how to efficiently and effectively transfer knowledge in a vision transformer. We propose consolidator to modify the pre-trained model with the addition of a small set of tunable parameters. Our consolidator can reach up to 7.56 better accuracy than full fine-tuning with merely 0.35% parameters.
  arXiv  Detail & Related papers  (2023-04-30T23:59:02Z)
• Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning [85.55727213502402]
  We focus on improving the few-shot performance of prompt tuning by transferring knowledge from soft prompts of source tasks. We propose Sample-specific Ensemble of Source Models (SESoM) SESoM learns to adjust the contribution of each source model for each target sample separately when ensembling source model outputs.
  arXiv  Detail & Related papers  (2022-10-23T01:33:16Z)
• Prompt Tuning for Generative Multimodal Pretrained Models [75.44457974275154]
  We implement prompt tuning on the unified sequence-to-sequence pretrained model adaptive to both understanding and generation tasks. Experimental results demonstrate that the light-weight prompt tuning can achieve comparable performance with finetuning. In comparison with finetuned models, the prompt-tuned models demonstrate improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2022-08-04T08:56:38Z)
• Pro-tuning: Unified Prompt Tuning for Vision Tasks [133.12978197265596]
  Fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. In this work, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks.
  arXiv  Detail & Related papers  (2022-07-28T21:09:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.