One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning

• URL: http://arxiv.org/abs/2608.03249v1
• Date: Tue, 04 Aug 2026 07:21:39 GMT
• Title: One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning
• Abstract summary: Cold-Start Active Learning (CSAL) aims to select a valuable subset from an unlabeled pool without prior knowledge or human assistance.<n>We argue that the real challenge is not to design yet another selection, but to make CSAL adapt automatically to the data and task at hand.<n>We present a novel Sinkhorn-based CSAL algorithm, termed $$-Adaptive Selection ($$-AS)
• Score: 19.504724272527515
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Cold-Start Active Learning (CSAL) aims to select a valuable subset from an unlabeled pool without any prior knowledge or human assistance. Existing methods take diverse routes based on typicality, coverage, or diversity. Each rests on its own inductive bias and therefore performs well on some tasks yet poorly on others. We argue that the real challenge is not to design yet another selection heuristic, but to make CSAL adapt automatically to the data and task at hand. To this end, we revisit CSAL through the lens of optimal transport. First, we propose a generalized transport selection framework that reveals the shared allocation structure of existing methods and exactly subsumes representative formulations. Second, we introduce a theoretical analysis that characterizes the trade-off controlled by entropic regularization and establishes a task-agnostic minimax bound for cold-start selection. These results provide a principled foundation for adapting the regularization strength to the unlabeled data. Third, we derive a data-adaptive regularization rule and present a novel Sinkhorn-based CSAL algorithm, termed $ε$-Adaptive Selection ($ε$-AS). Extensive experiments on six public datasets and multiple annotation budgets show that $ε$-AS consistently achieves state-of-the-art performance. On ImageNet-1k, it improves the average accuracy over ActiveFT by 1.29% while reducing selection time by 56.2%. Code will be released at https://github.com/Z-yiwei/OT-CSAL

Related papers

• REAR: Test-time Preference Realignment through Reward Decomposition [68.09214603569744]
  We introduce a novel framework that models the task as a realignment problem, since the base model often fails to align with the stated preference.<n>We derive a REAlignment Reward (REAR) that selectively rescales the proportions of these two reward terms.<n>We show that REAR can be formulated as a linear combination of token-level policy log-probabilities, making it computationally efficient and easy to integrate with various TTS algorithms.
  arXiv  Detail & Related papers  (2026-06-29T14:17:53Z)
• From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning [19.659110958894335]
  Supervised fine-tuning (SFT) data selection is commonly formulated as instance ranking.<n> effective SFT training subsets are often produced through ordered curation recipes.<n>We introduce AutoSelection, a two-layer solver that decouples fixed-pool materialization based on cached task-, data-, and model-side signals.
  arXiv  Detail & Related papers  (2026-05-13T03:27:21Z)
• Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance [92.72779885657373]
  We propose a framework that grounds model selection in the internal functional dynamics of the visual encoder.<n>Our approach represents each task via layer wise conductance and derives a target-conditioned block importance distribution through entropy regularized alignment.<n>Building on this, we introduce Directional Conductance Divergence (DCD), an asymmetric metric that quantifies how effectively a source task covers the target's salient functional blocks.
  arXiv  Detail & Related papers  (2026-02-01T17:29:43Z)
• SAND: One-Shot Feature Selection with Additive Noise Distortion [3.5976830118932583]
  We introduce a novel, non-intrusive feature selection layer that automatically identifies and selects the $k$ most informative features during neural network training.<n>Our method is uniquely simple, requiring no alterations to the loss function, network architecture, or post-selection retraining.<n>Our work demonstrates that simplicity and performance are not mutually exclusive, offering a powerful yet straightforward tool for feature selection in machine learning.
  arXiv  Detail & Related papers  (2025-05-06T18:59:35Z)
• SeWA: Selective Weight Average via Probabilistic Masking [51.015724517293236]
  We show that only a few points are needed to achieve better and faster convergence.<n>We transform the discrete selection problem into a continuous subset optimization framework.<n>We derive the SeWA's stability bounds, which are sharper than that under both convex image checkpoints.
  arXiv  Detail & Related papers  (2025-02-14T12:35:21Z)
• Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach [17.79010397902909]
  We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks.<n>This problem has broad applications in NLP, such as targeted instruction tuning and data selection in chain-of-thought fine-tuning.<n>We introduce a new algorithm for estimating model fine-tuning performance without requiring repeated training.
  arXiv  Detail & Related papers  (2024-09-28T21:26:50Z)
• Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning [17.40655778450583]
  We propose a principled metric named Variance Alignment Score (VAS), which has the form $langle Sigma_texttest, Sigma_irangle$. We show that applying VAS and CLIP scores together can outperform baselines by a margin of $1.3%$ on 38 evaluation sets for noisy dataset DataComp and $2.5%$ on VTAB for high-quality dataset CC12M.
  arXiv  Detail & Related papers  (2024-02-03T06:29:04Z)
• Towards Free Data Selection with General-Purpose Models [71.92151210413374]
  A desirable data selection algorithm can efficiently choose the most informative samples to maximize the utility of limited annotation budgets. Current approaches, represented by active learning methods, typically follow a cumbersome pipeline that iterates the time-consuming model training and batch data selection repeatedly. FreeSel bypasses the heavy batch selection process, achieving a significant improvement in efficiency and being 530x faster than existing active learning methods.
  arXiv  Detail & Related papers  (2023-09-29T15:50:14Z)
• ASPEST: Bridging the Gap Between Active Learning and Selective Prediction [56.001808843574395]
  Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples. In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
  arXiv  Detail & Related papers  (2023-04-07T23:51:07Z)
• Contextual Active Model Selection [10.925932167673764]
  We present an approach to actively select pre-trained models while minimizing labeling costs.<n>The objective is to adaptively select the best model to make a prediction while limiting label requests.<n>We propose CAMS, a contextual active model selection algorithm that relies on two novel components.
  arXiv  Detail & Related papers  (2022-07-13T08:22:22Z)
• A Lagrangian Duality Approach to Active Learning [119.36233726867992]
  We consider the batch active learning problem, where only a subset of the training data is labeled. We formulate the learning problem using constrained optimization, where each constraint bounds the performance of the model on labeled samples. We show, via numerical experiments, that our proposed approach performs similarly to or better than state-of-the-art active learning methods.
  arXiv  Detail & Related papers  (2022-02-08T19:18:49Z)
• Test-time Batch Statistics Calibration for Covariate Shift [66.7044675981449]
  We propose to adapt the deep models to the novel environment during inference. We present a general formulation $alpha$-BN to calibrate the batch statistics. We also present a novel loss function to form a unified test time adaptation framework Core.
  arXiv  Detail & Related papers  (2021-10-06T08:45:03Z)

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.