MetaRank: Task-Aware Metric Selection for Model Transferability Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yuhang, Zhao, Wenjie, Guo, Yunhui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917105477091328
author Liu, Yuhang
Zhao, Wenjie
Guo, Yunhui
author_facet Liu, Yuhang
Zhao, Wenjie
Guo, Yunhui
contents Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models without full fine-tuning. In practice, the choice of which MTE metric to use is often ad hoc or guided simply by a metric's average historical performance. However, we observe that the effectiveness of MTE metrics is highly task-dependent and no single metric is universally optimal across all target datasets. To address this gap, we introduce MetaRank, a meta-learning framework for automatic, task-aware MTE metric selection. We formulate metric selection as a learning-to-rank problem. Rather than relying on conventional meta-features, MetaRank encodes textual descriptions of both datasets and MTE metrics using a pretrained language model, embedding them into a shared semantic space. A meta-predictor is then trained offline on diverse meta-tasks to learn the intricate relationship between dataset characteristics and metric mechanisms, optimized with a listwise objective that prioritizes correctly ranking the top-performing metrics. During the subsequent online phase, MetaRank efficiently ranks the candidate MTE metrics for a new, unseen target dataset based on its textual description, enabling practitioners to select the most appropriate metric a priori. Extensive experiments across 11 pretrained models and 11 target datasets demonstrate the strong effectiveness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21007
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
Liu, Yuhang
Zhao, Wenjie
Guo, Yunhui
Computer Vision and Pattern Recognition
Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models without full fine-tuning. In practice, the choice of which MTE metric to use is often ad hoc or guided simply by a metric's average historical performance. However, we observe that the effectiveness of MTE metrics is highly task-dependent and no single metric is universally optimal across all target datasets. To address this gap, we introduce MetaRank, a meta-learning framework for automatic, task-aware MTE metric selection. We formulate metric selection as a learning-to-rank problem. Rather than relying on conventional meta-features, MetaRank encodes textual descriptions of both datasets and MTE metrics using a pretrained language model, embedding them into a shared semantic space. A meta-predictor is then trained offline on diverse meta-tasks to learn the intricate relationship between dataset characteristics and metric mechanisms, optimized with a listwise objective that prioritizes correctly ranking the top-performing metrics. During the subsequent online phase, MetaRank efficiently ranks the candidate MTE metrics for a new, unseen target dataset based on its textual description, enabling practitioners to select the most appropriate metric a priori. Extensive experiments across 11 pretrained models and 11 target datasets demonstrate the strong effectiveness of our approach.
title MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.21007