Pre-Trained Model Recommendation for Downstream Fine-tuning
- URL: http://arxiv.org/abs/2403.06382v1
- Date: Mon, 11 Mar 2024 02:24:32 GMT
- Title: Pre-Trained Model Recommendation for Downstream Fine-tuning
- Authors: Jiameng Bai, Sai Wu, Jie Song, Junbo Zhao, Gang Chen
- Abstract summary: Model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task.
Existing model selection techniques are often constrained in their scope and tend to overlook the nuanced relationships between models and tasks.
We present a pragmatic framework textbfFennec, delving into a diverse, large-scale model repository.
- Score: 22.343011779348682
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: As a fundamental problem in transfer learning, model selection aims to rank
off-the-shelf pre-trained models and select the most suitable one for the new
target task. Existing model selection techniques are often constrained in their
scope and tend to overlook the nuanced relationships between models and tasks.
In this paper, we present a pragmatic framework \textbf{Fennec}, delving into a
diverse, large-scale model repository while meticulously considering the
intricate connections between tasks and models. The key insight is to map all
models and historical tasks into a transfer-related subspace, where the
distance between model vectors and task vectors represents the magnitude of
transferability. A large vision model, as a proxy, infers a new task's
representation in the transfer space, thereby circumventing the computational
burden of extensive forward passes. We also investigate the impact of the
inherent inductive bias of models on transfer results and propose a novel
method called \textbf{archi2vec} to encode the intricate structures of models.
The transfer score is computed through straightforward vector arithmetic with a
time complexity of $\mathcal{O}(1)$. Finally, we make a substantial
contribution to the field by releasing a comprehensive benchmark. We validate
the effectiveness of our framework through rigorous testing on two benchmarks.
The benchmark and the code will be publicly available in the near future.
Related papers
- Occam's model: Selecting simpler representations for better transferability estimation [5.329941688969535]
We introduce two novel metrics for estimating the transferability of pre-trained models.
We rigorously evaluate the proposed metrics against state-of-the-art alternatives across diverse problem settings.
We experimentally show that our metrics increase Kendall's Tau by up to 32% compared to the state-of-the-art baselines.
arXiv Detail & Related papers (2025-02-10T18:23:24Z) - Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent [74.02034188307857]
Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data.
We find existing methods inevitably discard task-specific information that, while causing conflicts, is crucial for performance.
Our approach consistently outperforms previous methods, achieving state-of-the-art results across diverse architectures and tasks in both vision and NLP domains.
arXiv Detail & Related papers (2025-01-02T12:45:21Z) - Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging [33.23758947497205]
Advanced embedding models are typically developed using large-scale multi-task data and joint training across multiple tasks.
To overcome these challenges, we explore model merging-a technique that combines independently trained models to mitigate gradient conflicts and balance data distribution.
We introduce a novel method, Self Positioning, which efficiently searches for optimal model combinations within the space of task vectors using gradient descent.
arXiv Detail & Related papers (2024-10-19T08:39:21Z) - Deciphering Movement: Unified Trajectory Generation Model for Multi-Agent [53.637837706712794]
We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs.
Specifically, we introduce a Ghost Spatial Masking (GSM) module embedded within a Transformer encoder for spatial feature extraction.
We benchmark three practical sports game datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
arXiv Detail & Related papers (2024-05-27T22:15:23Z) - A Two-Phase Recall-and-Select Framework for Fast Model Selection [13.385915962994806]
We propose a two-phase (coarse-recall and fine-selection) model selection framework.
It aims to enhance the efficiency of selecting a robust model by leveraging the models' training performances on benchmark datasets.
It has been demonstrated that the proposed methodology facilitates the selection of a high-performing model at a rate about 3x times faster than conventional baseline methods.
arXiv Detail & Related papers (2024-03-28T14:44:44Z) - MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining [73.81862342673894]
Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks.
transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks.
We conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection.
Our models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection.
arXiv Detail & Related papers (2024-03-20T09:17:22Z) - Building a Winning Team: Selecting Source Model Ensembles using a
Submodular Transferability Estimation Approach [20.86345962679122]
Estimating the transferability of publicly available pretrained models to a target task has assumed an important place for transfer learning tasks.
We propose a novel Optimal tranSport-based suBmOdular tRaNsferability metric (OSBORN) to estimate the transferability of an ensemble of models to a downstream task.
arXiv Detail & Related papers (2023-09-05T17:57:31Z) - $\Delta$-Patching: A Framework for Rapid Adaptation of Pre-trained
Convolutional Networks without Base Performance Loss [71.46601663956521]
Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time.
We propose $Delta$-Patching for fine-tuning neural network models in an efficient manner, without the need to store model copies.
Our experiments show that $Delta$-Networks outperform earlier model patching work while only requiring a fraction of parameters to be trained.
arXiv Detail & Related papers (2023-03-26T16:39:44Z) - SynBench: Task-Agnostic Benchmarking of Pretrained Representations using
Synthetic Data [78.21197488065177]
Recent success in fine-tuning large models, that are pretrained on broad data at scale, on downstream tasks has led to a significant paradigm shift in deep learning.
This paper proposes a new task-agnostic framework, textitSynBench, to measure the quality of pretrained representations using synthetic data.
arXiv Detail & Related papers (2022-10-06T15:25:00Z) - How Well Do Sparse Imagenet Models Transfer? [75.98123173154605]
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" datasets.
In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset.
We show that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities.
arXiv Detail & Related papers (2021-11-26T11:58:51Z) - Deep Ensembles for Low-Data Transfer Learning [21.578470914935938]
We study different ways of creating ensembles from pre-trained models.
We show that the nature of pre-training itself is a performant source of diversity.
We propose a practical algorithm that efficiently identifies a subset of pre-trained models for any downstream dataset.
arXiv Detail & Related papers (2020-10-14T07:59:00Z)
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.