Scaling Up Temporal Domain Generalization via Temporal Experts Averaging

• URL: http://arxiv.org/abs/2509.26045v1
• Date: Tue, 30 Sep 2025 10:21:44 GMT
• Title: Scaling Up Temporal Domain Generalization via Temporal Experts Averaging
• Authors: Aoming Liu, Kevin Miller, Venkatesh Saligrama, Kate Saenko, Boqing Gong, Ser-Nam Lim, Bryan A. Plummer,
• Abstract summary: Temporal Domain Generalization aims to generalize across temporal distribution shifts, e.g., lexical change over time.<n>We propose Temporal Experts Averaging (TEA), a novel and scalable TDG framework that updates the entire model using weight averaging to maximize generalization potential.<n>We show TEA outperforms prior TDG methods by up to 69% while being up to 60x more efficient.
• Score: 108.44248708602221
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal Domain Generalization (TDG) aims to generalize across temporal distribution shifts, e.g., lexical change over time. Prior work often addresses this by predicting future model weights. However, full model prediction is prohibitively expensive for even reasonably sized models. Thus, recent methods only predict the classifier layer, limiting generalization by failing to adjust other model components. To address this, we propose Temporal Experts Averaging (TEA), a novel and scalable TDG framework that updates the entire model using weight averaging to maximize generalization potential while minimizing computational costs. Our theoretical analysis guides us to two steps that enhance generalization to future domains. First, we create expert models with functional diversity yet parameter similarity by fine-tuning a domain-agnostic base model on individual temporal domains while constraining weight changes. Second, we optimize the bias-variance tradeoff through adaptive averaging coefficients derived from modeling temporal weight trajectories in a principal component subspace. Expert's contributions are based on their projected proximity to future domains. Extensive experiments across 7 TDG benchmarks, 5 models, and 2 TDG settings shows TEA outperforms prior TDG methods by up to 69% while being up to 60x more efficient.

Related papers

• Domain Generalization for Time Series: Enhancing Drilling Regression Models for Stick-Slip Index Prediction [0.5277024349608834]
  The study aims to develop a robust regression model that can generalize across domains by training on 60 second labeled sequences of 1 Hz surface drilling data to predict the Stick-Slip Index (SSI)<n>A comparative analysis of the Adversarial Domain Generalization (ADG), Invariant Risk Minimization (IRM) and baseline models is presented, along with an evaluation of the effectiveness of transfer learning (TL) in improving model performance.
  arXiv  Detail & Related papers  (2026-01-06T10:09:42Z)
• Class-invariant Test-Time Augmentation for Domain Generalization [16.001258672237267]
  Domain generalization helps models generalize to unseen domains.<n>Most prior approaches rely on multi-domain training or computationally intensive test-time adaptation.<n>We propose a complementary strategy: lightweight test-time augmentation.
  arXiv  Detail & Related papers  (2025-09-17T20:42:23Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization [28.977757627384165]
  Domain Domain (DG) aims to avoid the performance degradation of the model when the distribution shift between the limited training data and unseen test data occurs. Recently, foundation models with enormous parameters have been pre-trained with huge datasets, demonstrating strong generalization ability. Our framework achieves SOTA performance on five DG benchmarks, while only requiring training a small number of parameters without adding additional testing cost.
  arXiv  Detail & Related papers  (2024-07-21T07:50:49Z)
• Domain Generalization Guided by Large-Scale Pre-Trained Priors [24.74398777539288]
  Domain generalization (DG) aims to train a model from limited source domains, allowing it to generalize to unknown target domains. We introduce Fine-Tune with Large-scale pre-trained Priors (FT-LP) FT-LP incorporates the pre-trained model as a prior into the DG fine-tuning process, ensuring that the model refers to its pre-trained model at each optimization step.
  arXiv  Detail & Related papers  (2024-06-09T03:32:32Z)
• Scaling and renormalization in high-dimensional regression [72.59731158970894]
  We present a unifying perspective on recent results on ridge regression.<n>We use the basic tools of random matrix theory and free probability, aimed at readers with backgrounds in physics and deep learning.<n>Our results extend and provide a unifying perspective on earlier models of scaling laws.
  arXiv  Detail & Related papers  (2024-05-01T15:59:00Z)
• Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach [54.429396802848224]
  This paper proposes an interpretable generative model for motion prediction with robust generalizability to out-of-distribution cases. For interpretability, the model achieves the target-driven motion prediction by estimating the spatial distribution of long-term destinations. Experiments on motion prediction datasets validate that the fitted model can be interpretable and generalizable.
  arXiv  Detail & Related papers  (2024-03-10T04:16:04Z)
• Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models [32.52492468276371]
  We propose regularized deep generative model (Reg-DGM) to reduce the variance of generative modeling with limited data. Reg-DGM uses a pre-trained model to optimize a weighted sum of a certain divergence and the expectation of an energy function. Empirically, with various pre-trained feature extractors and a data-dependent energy function, Reg-DGM consistently improves the generation performance of strong DGMs with limited data.
  arXiv  Detail & Related papers  (2022-08-30T10:28:50Z)
• Super-model ecosystem: A domain-adaptation perspective [101.76769818069072]
  This paper attempts to establish the theoretical foundation for the emerging super-model paradigm via domain adaptation. Super-model paradigms help reduce computational and data cost and carbon emission, which is critical to AI industry.
  arXiv  Detail & Related papers  (2022-08-30T09:09:43Z)
• ER: Equivariance Regularizer for Knowledge Graph Completion [107.51609402963072]
  We propose a new regularizer, namely, Equivariance Regularizer (ER) ER can enhance the generalization ability of the model by employing the semantic equivariance between the head and tail entities. The experimental results indicate a clear and substantial improvement over the state-of-the-art relation prediction methods.
  arXiv  Detail & Related papers  (2022-06-24T08:18:05Z)
• Domain Generalization using Pretrained Models without Fine-tuning [25.489714555859944]
  Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. We propose a novel domain generalization paradigm to better leverage various pretrained models, named specialized ensemble learning for domain generalization (SEDGE) SEDGE achieves significant performance improvements comparing to strong baselines including state-of-the-art method in DG tasks.
  arXiv  Detail & Related papers  (2022-03-09T09:33:59Z)
• Learning to Generate Novel Domains for Domain Generalization [115.21519842245752]
  This paper focuses on the task of learning from multiple source domains a model that generalizes well to unseen domains. We employ a data generator to synthesize data from pseudo-novel domains to augment the source domains. Our method, L2A-OT, outperforms current state-of-the-art DG methods on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-07-07T09:34:17Z)

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.