Efficient Stitchable Task Adaptation
- URL: http://arxiv.org/abs/2311.17352v2
- Date: Tue, 9 Jul 2024 01:54:18 GMT
- Title: Efficient Stitchable Task Adaptation
- Authors: Haoyu He, Zizheng Pan, Jing Liu, Jianfei Cai, Bohan Zhuang,
- Abstract summary: We present a novel framework, Efficient Stitchable Task Adaptation (ESTA), to efficiently produce a palette of fine-tuned models.
Specifically, we first tailor parameter-efficient fine-tuning to share low-rank updates among the stitches.
We streamline a simple yet effective one-stage deployment pipeline, which estimates the important stitches to deploy.
- Score: 47.94819192325723
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The paradigm of pre-training and fine-tuning has laid the foundation for deploying deep learning models. However, most fine-tuning methods are designed to meet a specific resource budget. Recently, considering diverse deployment scenarios with various resource budgets, SN-Net is introduced to quickly obtain numerous new networks (stitches) from the pre-trained models (anchors) in a model family via model stitching. Although promising, SN-Net confronts new challenges when adapting it to new target domains, including huge memory and storage requirements and a long and sub-optimal multistage adaptation process. In this work, we present a novel framework, Efficient Stitchable Task Adaptation (ESTA), to efficiently produce a palette of fine-tuned models that adhere to diverse resource constraints. Specifically, we first tailor parameter-efficient fine-tuning to share low-rank updates among the stitches while maintaining independent bias terms. In this way, we largely reduce fine-tuning memory burdens and mitigate the interference among stitches that arises in task adaptation. Furthermore, we streamline a simple yet effective one-stage deployment pipeline, which estimates the important stitches to deploy with training-time gradient statistics. By assigning higher sampling probabilities to important stitches, we also get a boosted Pareto frontier. Extensive experiments on 25 downstream visual recognition tasks demonstrate that our ESTA is capable of generating stitches with smooth accuracy-efficiency trade-offs and surpasses the direct SN-Net adaptation by remarkable margins with significantly lower training time and fewer trainable parameters. Furthermore, we demonstrate the flexibility and scalability of our ESTA framework by stitching LLMs from LLaMA family, obtaining chatbot stitches of assorted sizes. Source code is available at https://github.com/ziplab/Stitched_LLaMA
Related papers
- RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks [16.512587987753967]
RECAST is a novel method that dramatically reduces task-specific trainable parameters to fewer than 50.
We show that RECAST outperforms the state-of-the-art by up to 3% across various scales, architectures, and parameter spaces.
arXiv Detail & Related papers (2024-11-25T19:08:38Z) - LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging [80.17238673443127]
LiNeS is a post-training editing technique designed to preserve pre-trained generalization while enhancing fine-tuned task performance.
LiNeS demonstrates significant improvements in both single-task and multi-task settings across various benchmarks in vision and natural language processing.
arXiv Detail & Related papers (2024-10-22T16:26:05Z) - SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
We propose an innovative METL strategy called SHERL for resource-limited scenarios.
In the early route, intermediate outputs are consolidated via an anti-redundancy operation.
In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
arXiv Detail & Related papers (2024-07-10T10:22:35Z) - Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large
Language Models [46.92994945808424]
Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs)
This paper presents a comprehensive analysis of catastrophic forgetting in MLLMs and introduces a post-training adjustment method called Model Tailor.
arXiv Detail & Related papers (2024-02-19T11:02:05Z) - Building Variable-sized Models via Learngene Pool [39.99697115082106]
Recently, Stitchable Neural Networks (SN-Net) is proposed to stitch some pre-trained networks for building numerous networks with different complexity and performance trade-offs.
SN-Net faces challenges to build smaller models for low resource constraints.
We propose a novel method called Learngene Pool to overcome these challenges.
arXiv Detail & Related papers (2023-12-10T03:46:01Z) - TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series [57.4208255711412]
Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS)
We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks.
arXiv Detail & Related papers (2023-10-02T16:45:19Z) - One-Shot Pruning for Fast-adapting Pre-trained Models on Devices [28.696989086706186]
Large-scale pre-trained models have been remarkably successful in resolving downstream tasks.
deploying these models on low-capability devices still requires an effective approach, such as model pruning.
We present a scalable one-shot pruning method that leverages pruned knowledge of similar tasks to extract a sub-network from the pre-trained model for a new task.
arXiv Detail & Related papers (2023-07-10T06:44:47Z) - Stitchable Neural Networks [40.8842135978138]
We present Stitchable Neural Networks (SN-Net), a novel scalable and efficient framework for model deployment.
SN-Net splits the anchors across the blocks/layers and then stitches them together with simple stitching layers to map the activations from one anchor to another.
Experiments on ImageNet classification demonstrate that SN-Net can obtain on-par or even better performance than many individually trained networks.
arXiv Detail & Related papers (2023-02-13T18:37:37Z) - Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for
Downstream Tasks [55.431048995662714]
We create a small model for a new task from the pruned models of similar tasks.
We show that a few fine-tuning steps on this model suffice to produce a promising pruned-model for the new task.
We develop a simple but effective ''Meta-Vote Pruning (MVP)'' method that significantly reduces the pruning iterations for a new task.
arXiv Detail & Related papers (2023-01-27T06:49:47Z) - Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers.
Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters.
We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
arXiv Detail & Related papers (2022-03-30T23:16:07Z)
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.