Where is the Truth? The Risk of Getting Confounded in a Continual World

• URL: http://arxiv.org/abs/2402.06434v2
• Date: Sat, 15 Jun 2024 13:37:31 GMT
• Title: Where is the Truth? The Risk of Getting Confounded in a Continual World
• Authors: Florian Peter Busch, Roshni Kamath, Rupert Mitchell, Wolfgang Stammer, Kristian Kersting, Martin Mundt,
• Abstract summary: A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In a continual learning setting where confounders may vary in time across tasks, the challenge of mitigating the effect of confounders far exceeds the standard forgetting problem.
• Score: 21.862370510786004
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting where confounders may vary in time across tasks, the challenge of mitigating the effect of confounders far exceeds the standard forgetting problem normally considered. In particular, we provide a formal description of such continual confounders and identify that, in general, spurious correlations are easily ignored when training for all tasks jointly, but it is harder to avoid confounding when they are considered sequentially. These descriptions serve as a basis for constructing a novel CLEVR-based continually confounded dataset, which we term the ConCon dataset. Our evaluations demonstrate that standard continual learning methods fail to ignore the dataset's confounders. Overall, our work highlights the challenges of confounding factors, particularly in continual learning settings, and demonstrates the need for developing continual learning methods to robustly tackle these.

Related papers

• Decoupling the Class Label and the Target Concept in Machine Unlearning [81.69857244976123]
  Machine unlearning aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previous studies showed that class-wise unlearning is successful in forgetting the knowledge of a target class. We propose a general framework, namely, TARget-aware Forgetting (TARF)
  arXiv  Detail & Related papers  (2024-06-12T14:53:30Z)
• Continual Learning in the Presence of Spurious Correlation [23.999136417157597]
  We show that standard continual learning algorithms can transfer biases from one task to another, both forward and backward. We propose a plug-in method for debiasing-aware continual learning, dubbed as Group-class Balanced Greedy Sampling (BGS)
  arXiv  Detail & Related papers  (2023-03-21T14:06:12Z)
• Learning from Data Streams: An Overview and Update [1.5076964620370268]
  We reformulate the fundamental definitions and settings of supervised data-stream learning. We take a fresh look at what constitutes a supervised data-stream learning task. Our main emphasis is that learning from data streams does not impose a single-pass or online-learning approach.
  arXiv  Detail & Related papers  (2022-12-30T14:01:41Z)
• Data Poisoning Attack Aiming the Vulnerability of Continual Learning [25.480762565632332]
  We present a simple task-specific data poisoning attack that can be used in the learning process of a new task. We experiment with the attack on the two representative regularization-based continual learning methods.
  arXiv  Detail & Related papers  (2022-11-29T02:28:05Z)
• Towards Federated Long-Tailed Learning [76.50892783088702]
  Data privacy and class imbalance are the norm rather than the exception in many machine learning tasks. Recent attempts have been launched to, on one side, address the problem of learning from pervasive private data, and on the other side, learn from long-tailed data. This paper focuses on learning with long-tailed (LT) data distributions under the context of the popular privacy-preserved federated learning (FL) framework.
  arXiv  Detail & Related papers  (2022-06-30T02:34:22Z)
• Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship [54.73817402934303]
  We propose Experience Continual Replay (ERR), a bi-level learning framework to adaptively tune task-wise to achieve a better stability plasticity' tradeoff. ERR can consistently improve the performance of all baselines and surpass current state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-31T12:05:22Z)
• Towards Realistic Single-Task Continuous Learning Research for NER [19.61159414320659]
  We discuss some of the unrealistic data characteristics of public datasets and study the challenges of realistic single-task continuous learning. We construct a CL NER dataset from an existing publicly available dataset and release it along with the code to the research community.
  arXiv  Detail & Related papers  (2021-10-27T18:23:31Z)
• Stateful Offline Contextual Policy Evaluation and Learning [88.9134799076718]
  We study off-policy evaluation and learning from sequential data. We formalize the relevant causal structure of problems such as dynamic personalized pricing. We show improved out-of-sample policy performance in this class of relevant problems.
  arXiv  Detail & Related papers  (2021-10-19T16:15:56Z)
• On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning [69.48387059607387]
  We consider the problem of using expert data with unobserved confounders for imitation and reinforcement learning. We analyze the limitations of learning from confounded expert data with and without external reward. We validate our claims empirically on challenging assistive healthcare and recommender system simulation tasks.
  arXiv  Detail & Related papers  (2021-10-13T07:31:31Z)
• Competency Problems: On Finding and Removing Artifacts in Language Data [50.09608320112584]
  We argue that for complex language understanding tasks, all simple feature correlations are spurious. We theoretically analyze the difficulty of creating data for competency problems when human bias is taken into account.
  arXiv  Detail & Related papers  (2021-04-17T21:34:10Z)
• A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning [8.188575923130662]
  We argue that notable lessons from open set recognition, the identification of statistically deviating data outside of the observed dataset, and the adjacent field of active learning, are frequently overlooked in the deep learning era. Our results show that this not only benefits each individual paradigm, but highlights the natural synergies in a common framework.
  arXiv  Detail & Related papers  (2020-09-03T16:56:36Z)

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.