Directed Structural Adaptation to Overcome Statistical Conflicts and Enable Continual Learning

• URL: http://arxiv.org/abs/2412.04190v1
• Date: Thu, 05 Dec 2024 14:30:18 GMT
• Title: Directed Structural Adaptation to Overcome Statistical Conflicts and Enable Continual Learning
• Authors: Zeki Doruk Erden, Boi Faltings,
• Abstract summary: We propose a structural adaptation method, DIRAD, that can complexify as needed and in a directed manner without being limited by statistical conflicts within a dataset.<n>We then extend this method and present the PREVAL framework, designed to prevent "catastrophic forgetting" in continual learning.<n>We show the reliability of the DIRAD in growing a network with high performance and orders-of-magnitude simpler than fixed topology networks.
• Score: 15.376349115976534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adaptive networks today rely on overparameterized fixed topologies that cannot break through the statistical conflicts they encounter in the data they are exposed to, and are prone to "catastrophic forgetting" as the network attempts to reuse the existing structures to learn new task. We propose a structural adaptation method, DIRAD, that can complexify as needed and in a directed manner without being limited by statistical conflicts within a dataset. We then extend this method and present the PREVAL framework, designed to prevent "catastrophic forgetting" in continual learning by detection of new data and assigning encountered data to suitable models adapted to process them, without needing task labels anywhere in the workflow. We show the reliability of the DIRAD in growing a network with high performance and orders-of-magnitude simpler than fixed topology networks; and demonstrate the proof-of-concept operation of PREVAL, in which continual adaptation to new tasks is observed while being able to detect and discern previously-encountered tasks.

Related papers

• Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation [67.80294336559574]
  Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios.<n>We propose a novel pipeline, Orthogonal Projection Subspace to aggregate online Prior-knowledge, dubbed OoPk.
  arXiv  Detail & Related papers  (2025-06-23T18:17:39Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [55.914891182214475]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• FRET: Feature Redundancy Elimination for Test Time Adaptation [4.793572485305334]
  Test-Time Adaptation (TTA) aims to enhance the generalization of deep learning models when faced with test data that exhibits distribution shifts from the training data.<n>In practice, we observe that feature redundancy in embeddings tends to increase as domain shifts intensify in TTA.<n>We introduce Feature Redundancy Elimination for Test-time Adaptation (FRET), a novel perspective for TTA.
  arXiv  Detail & Related papers  (2025-05-15T18:22:56Z)
• Valid Bootstraps for Networks with Applications to Network Visualisation [0.0]
  Quantifying uncertainty in networks is an important step in modelling relationships and interactions between entities. We consider the challenge of bootstrapping an inhomogeneous random graph when only a single observation of the network is made. We propose a principled, novel, distribution-free network bootstrap using k-nearest neighbour smoothing.
  arXiv  Detail & Related papers  (2024-10-28T10:22:22Z)
• Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation [49.53202761595912]
  Continual Test-Time Adaptation involves adapting a pre-trained source model to continually changing unsupervised target domains. We analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream.
  arXiv  Detail & Related papers  (2024-07-12T15:48:40Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Cross-Inferential Networks for Source-free Unsupervised Domain Adaptation [17.718392065388503]
  We propose to explore a new method called cross-inferential networks (CIN) Our main idea is that, when we adapt the network model to predict the sample labels from encoded features, we use these prediction results to construct new training samples with derived labels. Our experimental results on benchmark datasets demonstrate that our proposed CIN approach can significantly improve the performance of source-free UDA.
  arXiv  Detail & Related papers  (2023-06-29T14:04:24Z)
• Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion [50.03041373044267]
  We propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Learning. Experiments show that CFL achieves state-of-the-art performance and has a stronger ability to overcome compared with the classification baselines.
  arXiv  Detail & Related papers  (2023-05-20T19:22:40Z)
• 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)
• Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation [127.6168183074427]
  We propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data of the target environments. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation.
  arXiv  Detail & Related papers  (2021-12-13T13:19:45Z)
• Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks [103.14809802212535]
  We build on the generative adversarial networks (GANs) framework to address the problem of estimating the effect of continuous-valued interventions. Our model, SCIGAN, is flexible and capable of simultaneously estimating counterfactual outcomes for several different continuous interventions. To address the challenges presented by shifting to continuous interventions, we propose a novel architecture for our discriminator.
  arXiv  Detail & Related papers  (2020-02-27T18:46:21Z)

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.