Learning to Defer to a Population: A Meta-Learning Approach

• URL: http://arxiv.org/abs/2403.02683v2
• Date: Mon, 13 May 2024 05:42:03 GMT
• Title: Learning to Defer to a Population: A Meta-Learning Approach
• Authors: Dharmesh Tailor, Aditya Patra, Rajeev Verma, Putra Manggala, Eric Nalisnick,
• Abstract summary: We formulate an L2D system that can cope with never-before-seen experts at test-time. We employ an attention mechanism that is able to look for points in the context set that are similar to a given test point. In the experiments, we validate our methods on image recognition, traffic sign detection, and skin lesion diagnosis benchmarks.
• Score: 4.64209268422757
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert. All existing work on L2D assumes that each expert is well-identified, and if any expert were to change, the system should be re-trained. In this work, we alleviate this constraint, formulating an L2D system that can cope with never-before-seen experts at test-time. We accomplish this by using meta-learning, considering both optimization- and model-based variants. Given a small context set to characterize the currently available expert, our framework can quickly adapt its deferral policy. For the model-based approach, we employ an attention mechanism that is able to look for points in the context set that are similar to a given test point, leading to an even more precise assessment of the expert's abilities. In the experiments, we validate our methods on image recognition, traffic sign detection, and skin lesion diagnosis benchmarks.

Related papers

• Generate to Discriminate: Expert Routing for Continual Learning [59.71853576559306]
  Generate to Discriminate (G2D) is a continual learning method that leverages synthetic data to train a domain-discriminator. We observe that G2D outperforms competitive domain-incremental learning methods on tasks in both vision and language modalities.
  arXiv  Detail & Related papers  (2024-12-22T13:16:28Z)
• Informed Decision-Making through Advancements in Open Set Recognition and Unknown Sample Detection [0.0]
  Open set recognition (OSR) aims to bring classification tasks in a situation that is more like reality. This study provides an algorithm exploring a new representation of feature space to improve classification in OSR tasks.
  arXiv  Detail & Related papers  (2024-05-09T15:15:34Z)
• RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
  We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
  arXiv  Detail & Related papers  (2023-11-21T21:05:21Z)
• Interpretable Anomaly Detection via Discrete Optimization [1.7150329136228712]
  We propose a framework for learning inherently interpretable anomaly detectors from sequential data. We show that this problem is computationally hard and develop two learning algorithms based on constraint optimization. Using a prototype implementation, we demonstrate that our approach shows promising results in terms of accuracy and F1 score.
  arXiv  Detail & Related papers  (2023-03-24T16:19:15Z)
• A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems [128.63953314853327]
  "Lifelong Learning" systems are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. We show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems.
  arXiv  Detail & Related papers  (2023-01-18T21:58:54Z)
• Fully Automated Binary Pattern Extraction For Finger Vein Identification using Double Optimization Stages-Based Unsupervised Learning Approach [0.0]
  Machine learning-based unsupervised, supervised, and deep learning algorithms have had a significant influence on finger vein detection and recognition. Deep learning necessitates a large number of training datasets that must be manually produced and labeled. In this research, we offer a completely automated unsupervised learning strategy for training dataset creation.
  arXiv  Detail & Related papers  (2022-05-08T11:01:25Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)
• Robust Asymmetric Learning in POMDPs [24.45409442047289]
  Existing approaches for imitation learning have a serious flaw: the expert does not know what the trainee cannot see. We derive an objective to train the expert to maximize the expected reward of the imitating agent policy, and use it to construct an efficient algorithm, adaptive asymmetric DAgger (A2D) We show that A2D produces an expert policy that the agent can safely imitate, in turn outperforming policies learned by imitating a fixed expert.
  arXiv  Detail & Related papers  (2020-12-31T11:46:51Z)
• Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification [106.08067870620218]
  We propose a self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME) We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. We conduct extensive experiments and demonstrate that our method is able to achieve superior performances compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-06T12:57:36Z)
• A System for Real-Time Interactive Analysis of Deep Learning Training [66.06880335222529]
  Currently available systems are limited to monitoring only the logged data that must be specified before the training process starts. We present a new system that enables users to perform interactive queries on live processes generating real-time information.
  arXiv  Detail & Related papers  (2020-01-05T11:33:31Z)

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.