MetaRank: Task-Aware Metric Selection for Model Transferability Estimation

• URL: http://arxiv.org/abs/2511.21007v1
• Date: Wed, 26 Nov 2025 03:15:13 GMT
• Title: MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
• Authors: Yuhang Liu, Wenjie Zhao, Yunhui Guo,
• Abstract summary: We introduce MetaRank, a meta-learning framework for automatic, task-aware MTE metric selection.<n>Rather than relying on conventional meta-features, MetaRank encodes textual descriptions of both datasets and MTE metrics.<n>A meta-predictor is then trained offline on diverse meta-tasks to learn the intricate relationship between dataset characteristics and metric mechanisms.
• Score: 25.11923464702804
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning [9.851186633544975]
  We propose Meta-Sel, a lightweight supervised meta-learning approach for intent classification.<n>It learns a fast, interpretable scoring function for (candidate, query) pairs from labeled training data.<n>At inference time, the selector performs a single vectorized scoring over the full candidate pool and returns the top-k demonstrations.
  arXiv  Detail & Related papers  (2026-02-12T16:11:29Z)
• Large Language Models are Demonstration Pre-Selectors for Themselves [57.101804269100185]
  In-context learning (ICL) with large language models (LLMs) delivers strong few-shot performance by choosing few-shot demonstrations from the entire training data.<n>FEw yet Essential Demonstration prE-selectoR is a novel pre-selection framework that identifies a representative subset of demonstrations.<n>FEw yet Essential Demonstration prE-selectoR can reduce training data size by over 20% while maintaining performance.
  arXiv  Detail & Related papers  (2025-06-06T12:29:03Z)
• BeST -- A Novel Source Selection Metric for Transfer Learning [35.32994166809785]
  We develop a novel task-similarity metric (BeST) to identify the most transferrable source(s) for a given task.<n>Our metric can provide significant computational savings for transfer learning from a selection of a large number of possible source models.
  arXiv  Detail & Related papers  (2025-01-19T03:58:05Z)
• Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks [0.0]
  We show how statistical methodology can be used for quantifying uncertainty in metrics that have been aggregated across multiple tasks.<n>These techniques reveal insights such as the dominance of a specific model for certain types of tasks despite an overall poor performance.
  arXiv  Detail & Related papers  (2025-01-08T02:17:34Z)
• DsDm: Model-Aware Dataset Selection with Datamodels [81.01744199870043]
  Standard practice is to filter for examples that match human notions of data quality. We find that selecting according to similarity with "high quality" data sources may not increase (and can even hurt) performance compared to randomly selecting data. Our framework avoids handpicked notions of data quality, and instead models explicitly how the learning process uses train datapoints to predict on the target tasks.
  arXiv  Detail & Related papers  (2024-01-23T17:22:00Z)
• Transferability Metrics for Object Detection [0.0]
  Transfer learning aims to make the most of existing pre-trained models to achieve better performance on a new task in limited data scenarios. We extend transferability metrics to object detection using ROI-Align and TLogME. We show that TLogME provides a robust correlation with transfer performance and outperforms other transferability metrics on local and global level features.
  arXiv  Detail & Related papers  (2023-06-27T08:49:31Z)
• Meta-Regularization by Enforcing Mutual-Exclusiveness [0.8057006406834467]
  We propose a regularization technique for meta-learning models that gives the model designer more control over the information flow during meta-training. Our proposed regularization function shows an accuracy boost of $sim$ $36%$ on the Omniglot dataset.
  arXiv  Detail & Related papers  (2021-01-24T22:57:19Z)
• Meta-Generating Deep Attentive Metric for Few-shot Classification [53.07108067253006]
  We present a novel deep metric meta-generation method to generate a specific metric for a new few-shot learning task. In this study, we structure the metric using a three-layer deep attentive network that is flexible enough to produce a discriminative metric for each task. We gain surprisingly obvious performance improvement over state-of-the-art competitors, especially in the challenging cases.
  arXiv  Detail & Related papers  (2020-12-03T02:07:43Z)
• Improving Generalization in Meta-learning via Task Augmentation [69.83677015207527]
  We propose two task augmentation methods, including MetaMix and Channel Shuffle. Both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets.
  arXiv  Detail & Related papers  (2020-07-26T01:50:42Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)
• Incremental Meta-Learning via Indirect Discriminant Alignment [118.61152684795178]
  We develop a notion of incremental learning during the meta-training phase of meta-learning. Our approach performs favorably at test time as compared to training a model with the full meta-training set.
  arXiv  Detail & Related papers  (2020-02-11T01:39:12Z)

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.