A Two-Stage Learning-to-Defer Approach for Multi-Task Learning

• URL: http://arxiv.org/abs/2410.15729v3
• Date: Mon, 03 Feb 2025 04:12:17 GMT
• Title: A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
• Authors: Yannis Montreuil, Shu Heng Yeo, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi,
• Abstract summary: We introduce a novel Two-Stage Learning-to-Defer framework for multi-task learning that jointly addresses classification and regression tasks. We validate our framework on two challenging tasks: object detection, where classification and regression are tightly coupled, and electronic health record analysis.
• Score: 3.4289478404209826
• License:
• Abstract: The Two-Stage Learning-to-Defer framework has been extensively studied for classification and, more recently, regression tasks. However, many contemporary applications involve both classification and regression in an interdependent manner. In this work, we introduce a novel Two-Stage Learning-to-Defer framework for multi-task learning that jointly addresses these tasks. Our approach leverages a two-stage surrogate loss family, which we prove to be both ($\mathcal{G}, \mathcal{R}$)-consistent and Bayes-consistent, providing strong theoretical guarantees of convergence to the Bayes-optimal rejector. We establish consistency bounds explicitly linked to the cross-entropy surrogate family and the $L_1$-norm of the agents' costs, extending the theoretical minimizability gap analysis to the two-stage setting with multiple experts. We validate our framework on two challenging tasks: object detection, where classification and regression are tightly coupled, and existing methods fail, and electronic health record analysis, in which we highlight the suboptimality of current learning-to-defer approaches.

Related papers

• Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees [3.6787328174619254]
  Learning-to-Defer (L2D) facilitates optimal task allocation between AI systems and decision-makers. This paper conducts the first comprehensive analysis of adversarial robustness in two-stage L2D frameworks. We propose SARD, a robust, convex, deferral algorithm rooted in Bayes and $(mathcalR,mathcalG)$-consistency.
  arXiv  Detail & Related papers  (2025-02-03T03:44:35Z)
• Regression with Multi-Expert Deferral [30.389055604165222]
  Learning to defer with multiple experts is a framework where the learner can choose to defer the prediction to several experts. We present a novel framework of regression with deferral, which involves deferring the prediction to multiple experts. We introduce new surrogate loss functions for both scenarios and prove that they are supported by $H$-consistency bounds.
  arXiv  Detail & Related papers  (2024-03-28T15:26:38Z)
• Inter- and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentation [21.973620376753594]
  hierarchical prediction uncertainty within the student model (intra-uncertainty) and image prediction uncertainty (inter-uncertainty) have not been fully utilized by existing methods. We propose a novel inter- and intra-uncertainty regularization method to measure and constrain both inter- and intra-inconsistencies in the teacher-student architecture. We also propose a new two-stage network with pseudo-mask guided feature aggregation (PG-FANet) as the segmentation model.
  arXiv  Detail & Related papers  (2024-03-19T14:32:21Z)
• A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning [63.20009081099896]
  We provide a unifying framework for the design and analysis of multicalibrated predictors. We exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multicalibration learning problems.
  arXiv  Detail & Related papers  (2023-02-21T18:24:17Z)
• Hierarchical Optimization-Derived Learning [58.69200830655009]
  We establish a new framework, named Hierarchical ODL (HODL), to simultaneously investigate the intrinsic behaviors of optimization-derived model construction and its corresponding learning process. This is the first theoretical guarantee for these two coupled ODL components: optimization and learning.
  arXiv  Detail & Related papers  (2023-02-11T03:35:13Z)
• Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning [79.83792914684985]
  We prove a new identifiability result that provides conditions under which maximally sparse base-predictors yield disentangled representations. Motivated by this theoretical result, we propose a practical approach to learn disentangled representations based on a sparsity-promoting bi-level optimization problem.
  arXiv  Detail & Related papers  (2022-11-26T21:02:09Z)
• On the pitfalls of entropy-based uncertainty for multi-class semi-supervised segmentation [8.464487190628395]
  Semi-supervised learning has emerged as an appealing strategy to train deep models with limited supervision. We demonstrate in this work that this strategy leads to suboptimal results in a multi-class context. We propose an alternative solution to compute the uncertainty in a multi-class setting, based on divergence distances and which account for inter-class overlap.
  arXiv  Detail & Related papers  (2022-03-07T18:35:17Z)
• In Defense of the Unitary Scalarization for Deep Multi-Task Learning [121.76421174107463]
  We present a theoretical analysis suggesting that many specialized multi-tasks can be interpreted as forms of regularization. We show that, when coupled with standard regularization and stabilization techniques, unitary scalarization matches or improves upon the performance of complex multitasks.
  arXiv  Detail & Related papers  (2022-01-11T18:44:17Z)
• Adversarial Robustness with Semi-Infinite Constrained Learning [177.42714838799924]
  Deep learning to inputs perturbations has raised serious questions about its use in safety-critical domains. We propose a hybrid Langevin Monte Carlo training approach to mitigate this issue. We show that our approach can mitigate the trade-off between state-of-the-art performance and robust robustness.
  arXiv  Detail & Related papers  (2021-10-29T13:30:42Z)
• Multi-task Supervised Learning via Cross-learning [102.64082402388192]
  We consider a problem known as multi-task learning, consisting of fitting a set of regression functions intended for solving different tasks. In our novel formulation, we couple the parameters of these functions, so that they learn in their task specific domains while staying close to each other. This facilitates cross-fertilization in which data collected across different domains help improving the learning performance at each other task.
  arXiv  Detail & Related papers  (2020-10-24T21:35:57Z)

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.