Regularizing Second-Order Influences for Continual Learning

• URL: http://arxiv.org/abs/2304.10177v1
• Date: Thu, 20 Apr 2023 09:30:35 GMT
• Title: Regularizing Second-Order Influences for Continual Learning
• Authors: Zhicheng Sun, Yadong Mu, Gang Hua
• Abstract summary: Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by rehearsing on a small buffer holding the seen data. We dissect the interaction of sequential selection steps within a framework built on influence functions.
• Score: 39.16131410356833
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by rehearsing on a small buffer holding the seen data, for which a delicate sample selection strategy is required. However, existing selection schemes typically seek only to maximize the utility of the ongoing selection, overlooking the interference between successive rounds of selection. Motivated by this, we dissect the interaction of sequential selection steps within a framework built on influence functions. We manage to identify a new class of second-order influences that will gradually amplify incidental bias in the replay buffer and compromise the selection process. To regularize the second-order effects, a novel selection objective is proposed, which also has clear connections to two widely adopted criteria. Furthermore, we present an efficient implementation for optimizing the proposed criterion. Experiments on multiple continual learning benchmarks demonstrate the advantage of our approach over state-of-the-art methods. Code is available at https://github.com/feifeiobama/InfluenceCL.

Related papers

• Bidirectional Decoding: Improving Action Chunking via Closed-Loop Resampling [51.38330727868982]
  Bidirectional Decoding (BID) is a test-time inference algorithm that bridges action chunking with closed-loop operations. We show that BID boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• Large-Scale Sequential Learning for Recommender and Engineering Systems [91.3755431537592]
  In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions. The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach for faults detection in power grid.
  arXiv  Detail & Related papers  (2022-05-13T21:09:41Z)
• An Investigation of Replay-based Approaches for Continual Learning [79.0660895390689]
  Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF) Several solution classes have been proposed, of which so-called replay-based approaches seem very promising due to their simplicity and robustness. We empirically investigate replay-based approaches of continual learning and assess their potential for applications.
  arXiv  Detail & Related papers  (2021-08-15T15:05:02Z)
• MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
  Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
  arXiv  Detail & Related papers  (2021-07-23T06:57:08Z)
• Targeted Active Learning for Bayesian Decision-Making [15.491942513739676]
  We argue that when acquiring samples sequentially, separating learning and decision-making is sub-optimal. We introduce a novel active learning strategy which takes the down-the-line decision problem into account. Specifically, we introduce a novel active learning criterion which maximizes the expected information gain on the posterior distribution of the optimal decision.
  arXiv  Detail & Related papers  (2021-06-08T09:05:43Z)
• Toward Optimal Probabilistic Active Learning Using a Bayesian Approach [4.380488084997317]
  Active learning aims at reducing the labeling costs by an efficient and effective allocation of costly labeling resources. By reformulating existing selection strategies within our proposed model, we can explain which aspects are not covered in current state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-02T15:59:42Z)
• Fast Template Matching and Update for Video Object Tracking and Segmentation [56.465510428878]
  The main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames. The challenges lie in the selection of the matching method to predict the result as well as to decide whether to update the target template. We propose a novel approach which utilizes reinforcement learning to make these two decisions at the same time.
  arXiv  Detail & Related papers  (2020-04-16T08:58:45Z)

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.