Decentralizing Test-time Adaptation under Heterogeneous Data Streams
- URL: http://arxiv.org/abs/2411.15173v1
- Date: Sat, 16 Nov 2024 12:29:59 GMT
- Title: Decentralizing Test-time Adaptation under Heterogeneous Data Streams
- Authors: Zixian Su, Jingwei Guo, Xi Yang, Qiufeng Wang, Kaizhu Huang,
- Abstract summary: Test-Time Adaptation (TTA) has shown promise in addressing distribution shifts between training and testing data.<n>Previous attempts merely stabilize model fine-tuning over time to handle continually changing environments.<n>This paper delves into TTA under heterogeneous data streams, moving beyond current model-centric limitations.
- Score: 21.40129321379529
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While Test-Time Adaptation (TTA) has shown promise in addressing distribution shifts between training and testing data, its effectiveness diminishes with heterogeneous data streams due to uniform target estimation. As previous attempts merely stabilize model fine-tuning over time to handle continually changing environments, they fundamentally assume a homogeneous target domain at any moment, leaving the intrinsic real-world data heterogeneity unresolved. This paper delves into TTA under heterogeneous data streams, moving beyond current model-centric limitations. By revisiting TTA from a data-centric perspective, we discover that decomposing samples into Fourier space facilitates an accurate data separation across different frequency levels. Drawing from this insight, we propose a novel Frequency-based Decentralized Adaptation (FreDA) framework, which transitions data from globally heterogeneous to locally homogeneous in Fourier space and employs decentralized adaptation to manage diverse distribution shifts.Interestingly, we devise a novel Fourier-based augmentation strategy to assist in decentralizing adaptation, which individually enhances sample quality for capturing each type of distribution shifts. Extensive experiments across various settings (corrupted, natural, and medical environments) demonstrate the superiority of our proposed framework over the state-of-the-arts.
Related papers
- HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation [12.655334562608314]
Federated Learning (FL) is a decentralized approach where multiple clients collaboratively train a shared global model without sharing their raw data.<n>This paper introduces Hierarchical Federated Domain Generalization (HFedDG), a novel scenario designed to investigate domain shift within hierarchical architectures.
arXiv Detail & Related papers (2025-08-07T08:14:52Z) - Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
arXiv Detail & Related papers (2025-07-13T12:56:59Z) - ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains [17.357842682605185]
ReservoirTTA is a novel plug-in framework designed for prolonged test-time adaptation.<n>At its core, ReservoirTTA maintains a reservoir of domain-specialized models.<n>Our theoretical analysis reveals key components that bound parameter variance and prevent model collapse.
arXiv Detail & Related papers (2025-05-20T15:39:20Z) - PreAdaptFWI: Pretrained-Based Adaptive Residual Learning for Full-Waveform Inversion Without Dataset Dependency [8.719356558714246]
Full-waveform inversion (FWI) is a method that utilizes seismic data to invert the physical parameters of subsurface media.
Due to its ill-posed nature, FWI is susceptible to getting trapped in local minima.
Various research efforts have attempted to combine neural networks with FWI to stabilize the inversion process.
arXiv Detail & Related papers (2025-02-17T15:30:17Z) - Federated Learning with Sample-level Client Drift Mitigation [15.248811557566128]
Federated Learning suffers from severe performance degradation due to data heterogeneity among clients.
We propose FedBSS that first mitigates the heterogeneity issue in a sample-level manner.
We also achieved effective results on feature distribution and noise label dataset setting.
arXiv Detail & Related papers (2025-01-20T09:44:07Z) - Improving Distribution Alignment with Diversity-based Sampling [0.0]
Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data.
This paper proposes to improve these estimates by inducing diversity in each sampled minibatch.
It simultaneously balances the data and reduces the variance of the gradients, thereby enhancing the model's generalisation ability.
arXiv Detail & Related papers (2024-10-05T17:26:03Z) - Federated Impression for Learning with Distributed Heterogeneous Data [19.50235109938016]
Federated learning (FL) provides a paradigm that can learn from distributed datasets across clients without requiring them to share data.
In FL, sub-optimal convergence is common among data from different health centers due to the variety in data collection protocols and patient demographics across centers.
We propose FedImpres which alleviates catastrophic forgetting by restoring synthetic data that represents the global information as federated impression.
arXiv Detail & Related papers (2024-09-11T15:37:52Z) - Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment [59.75420353684495]
Machine learning applications on signals such as computer vision or biomedical data often face challenges due to the variability that exists across hardware devices or session recordings.
In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities.
We show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings.
arXiv Detail & Related papers (2024-07-19T13:33:38Z) - PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
We propose a.
Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns.
We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
arXiv Detail & Related papers (2024-06-04T13:51:08Z) - Deep Multi-Manifold Transformation Based Multivariate Time Series Fault Detection [22.005142941322912]
We propose a new method that combines a neighborhood-driven data augmentation strategy with a multi-manifold representation learning framework.<n>Our method achieves superior performance in terms of both accuracy and robustness, showing strong potential for generalization and real-world deployment.
arXiv Detail & Related papers (2024-05-25T14:48:04Z) - Collaborative Heterogeneous Causal Inference Beyond Meta-analysis [68.4474531911361]
We propose a collaborative inverse propensity score estimator for causal inference with heterogeneous data.
Our method shows significant improvements over the methods based on meta-analysis when heterogeneity increases.
arXiv Detail & Related papers (2024-04-24T09:04:36Z) - Invariant Anomaly Detection under Distribution Shifts: A Causal
Perspective [6.845698872290768]
Anomaly detection (AD) is the machine learning task of identifying highly discrepant abnormal samples.
Under the constraints of a distribution shift, the assumption that training samples and test samples are drawn from the same distribution breaks down.
We attempt to increase the resilience of anomaly detection models to different kinds of distribution shifts.
arXiv Detail & Related papers (2023-12-21T23:20:47Z) - Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers.
We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes.
We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
arXiv Detail & Related papers (2023-08-28T18:48:34Z) - Consistency Regularization for Generalizable Source-free Domain
Adaptation [62.654883736925456]
Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset.
Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets.
We propose a consistency regularization framework to develop a more generalizable SFDA method.
arXiv Detail & Related papers (2023-08-03T07:45:53Z) - Source-free Domain Adaptation Requires Penalized Diversity [60.04618512479438]
Source-free domain adaptation (SFDA) was introduced to address knowledge transfer between different domains in the absence of source data.
In unsupervised SFDA, the diversity is limited to learning a single hypothesis on the source or learning multiple hypotheses with a shared feature extractor.
We propose a novel unsupervised SFDA algorithm that promotes representational diversity through the use of separate feature extractors.
arXiv Detail & Related papers (2023-04-06T00:20:19Z) - FedAgg: Adaptive Federated Learning with Aggregated Gradients [1.5653612447564105]
We propose an adaptive FEDerated learning algorithm called FedAgg to alleviate the divergence between the local and average model parameters and obtain a fast model convergence rate.
We show that our framework is superior to existing state-of-the-art FL strategies for enhancing model performance and accelerating convergence rate under IID and Non-IID datasets.
arXiv Detail & Related papers (2023-03-28T08:07:28Z) - Integrating Local Real Data with Global Gradient Prototypes for
Classifier Re-Balancing in Federated Long-Tailed Learning [60.41501515192088]
Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively.
The data samples usually follow a long-tailed distribution in the real world, and FL on the decentralized and long-tailed data yields a poorly-behaved global model.
In this work, we integrate the local real data with the global gradient prototypes to form the local balanced datasets.
arXiv Detail & Related papers (2023-01-25T03:18:10Z) - Decentralized Local Stochastic Extra-Gradient for Variational
Inequalities [125.62877849447729]
We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices.
We make a very general assumption on the computational network that covers the settings of fully decentralized calculations.
We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
arXiv Detail & Related papers (2021-06-15T17:45:51Z) - GANs with Variational Entropy Regularizers: Applications in Mitigating
the Mode-Collapse Issue [95.23775347605923]
Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples.
GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution.
We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
arXiv Detail & Related papers (2020-09-24T19:34:37Z) - A Unified Theory of Decentralized SGD with Changing Topology and Local
Updates [70.9701218475002]
We introduce a unified convergence analysis of decentralized communication methods.
We derive universal convergence rates for several applications.
Our proofs rely on weak assumptions.
arXiv Detail & Related papers (2020-03-23T17:49:15Z)
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.