Referee-Meta-Learning for Fast Adaptation of Locational Fairness

• URL: http://arxiv.org/abs/2402.13379v1
• Date: Tue, 20 Feb 2024 21:09:04 GMT
• Title: Referee-Meta-Learning for Fast Adaptation of Locational Fairness
• Authors: Weiye Chen, Yiqun Xie, Xiaowei Jia, Erhu He, Han Bao, Bang An, Xun Zhou
• Abstract summary: We propose a locational meta-referee (Meta-Ref) to oversee the few-shot meta-training and meta-testing of a deep neural network. We show that Meta-Ref can improve locational fairness while keeping the overall prediction quality at a similar level.
• Score: 26.770426062329165
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When dealing with data from distinct locations, machine learning algorithms tend to demonstrate an implicit preference of some locations over the others, which constitutes biases that sabotage the spatial fairness of the algorithm. This unfairness can easily introduce biases in subsequent decision-making given broad adoptions of learning-based solutions in practice. However, locational biases in AI are largely understudied. To mitigate biases over locations, we propose a locational meta-referee (Meta-Ref) to oversee the few-shot meta-training and meta-testing of a deep neural network. Meta-Ref dynamically adjusts the learning rates for training samples of given locations to advocate a fair performance across locations, through an explicit consideration of locational biases and the characteristics of input data. We present a three-phase training framework to learn both a meta-learning-based predictor and an integrated Meta-Ref that governs the fairness of the model. Once trained with a distribution of spatial tasks, Meta-Ref is applied to samples from new spatial tasks (i.e., regions outside the training area) to promote fairness during the fine-tune step. We carried out experiments with two case studies on crop monitoring and transportation safety, which show Meta-Ref can improve locational fairness while keeping the overall prediction quality at a similar level.

Related papers

• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition [72.35438297011176]
  We propose a novel method to realize seamless adaptation of pre-trained models for visual place recognition (VPR) Specifically, to obtain both global and local features that focus on salient landmarks for discriminating places, we design a hybrid adaptation method. Experimental results show that our method outperforms the state-of-the-art methods with less training data and training time.
  arXiv  Detail & Related papers  (2024-02-22T12:55:01Z)
• Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts [11.562953837452126]
  We make the first attempt to assess the informativeness of local data derived from diverse domains. We propose a novel methodology termed Federated Evidential Active Learning (FEAL) to calibrate the data evaluation under domain shift.
  arXiv  Detail & Related papers  (2023-12-05T08:32:27Z)
• A Meta-learning based Generalizable Indoor Localization Model using Channel State Information [8.302375673936387]
  We propose a new meta-learning algorithm, TB-MAML, intended to further improve generalizability when the dataset is limited. We evaluate the performance of TB-MAML-based localization against conventionally trained localization models and localization done using other meta-learning algorithms.
  arXiv  Detail & Related papers  (2023-05-22T19:54:59Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy [75.63022284445945]
  We find that the existing works often build their few-shot model based on the image-level feature by mixing all local-level features. We present (a) a local-agnostic training strategy to avoid the discriminative location bias between the base and novel categories, and (b) a novel local-level similarity measure to capture the accurate comparison between local-level features.
  arXiv  Detail & Related papers  (2021-11-08T08:45:15Z)
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility [54.179859639868646]
  Bipartite ranking aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data. There have been rising concerns on whether the learned scoring function can cause systematic disparity across different protected groups. We propose a model post-processing framework for balancing them in the bipartite ranking scenario.
  arXiv  Detail & Related papers  (2020-06-15T10:08:39Z)
• Online Self-Supervised Learning for Object Picking: Detecting Optimum Grasping Position using a Metric Learning Approach [0.757024681220677]
  The optimal grasping position of an individual object is determined from the grasping score. The proposed online self-supervised learning method employs two deep neural networks.
  arXiv  Detail & Related papers  (2020-03-08T04:36:24Z)
• FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing [12.518673970373422]
  Data-driven learning model-based cooperative localization and location data processing are considered. We first review state-of-the-art algorithms in the context of federated learning. We demonstrate various practical use cases that are summarized from a mixture of standard, newly published, and unpublished works.
  arXiv  Detail & Related papers  (2020-03-08T01:51:56Z)

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.