PaperlayerView exact revision on arXiv

Source-linked AI summary

Learning to Generalize: Meta-Learning for Domain Generalization

Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales

arXiv:1710.03463v1cs.LG

TL;DR

Models trained under one domain's statistics can fail in novel domains, while domain generalization seeks robust performance without target-domain data. The paper introduces MLDG, which simulates train/test domain shift through virtual domains and aligns update directions, achieving state-of-the-art vision results and promising reinforcement-learning results. Its model-agnostic procedure applies across supervised and reinforcement-learning settings without constraining the base architecture.

  • Problem

    Domain shift causes models trained in one domain to perform poorly in target domains with different statistics, motivating domain generalization without target-domain training data.

    Source: Introduction · p. 1

  • Method

    MLDG is a model-agnostic meta-learning procedure that synthesizes virtual training and testing domains within minibatches and encourages training updates that also improve virtual testing loss.

    Source: Introduction · p. 2

  • Results

    MLDG achieves state-of-the-art results on a recent cross-domain image-recognition benchmark and promising results on two classic reinforcement-learning tasks.

    Source: Introduction · p. 2, Conclusion · p. 7

  • Takeaways & Limitations

    The approach provides a single training procedure for improving domain generalization across different base networks and both supervised and reinforcement-learning problems.

    Source: Introduction · p. 2

    The DG formulation assumes source and target domains share the same task, label space, and input feature space while differing in statistics.

    Source: Meta-Learning Domain Generalization · p. 2

Abstract

from arXiv · show

Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by producing models which by design generalize well to novel testing domains. We propose a novel {meta-learning} method for domain generalization. Rather than designing a specific model that is robust to domain shift as in most previous DG work, we propose a model agnostic training procedure for DG. Our algorithm simulates train/test domain shift during training by synthesizing virtual testing domains within each mini-batch. The meta-optimization objective requires that steps to improve training domain performance should also improve testing domain performance. This meta-learning procedure trains models with good generalization ability to novel domains. We evaluate our method and achieve state of the art results on a recent cross-domain image classification benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.

Introduction

Domain generalization seeks models that work in unseen domains without target-domain training data, addressing failures caused by domain shift. The paper introduces MLDG, a model-agnostic meta-learning procedure that simulates domain shift during training and reports strong results across vision and reinforcement learning.

Motivation

  • The paper frames domain generalization as a way to make models robust to changed conditions and perform well immediately in novel domains.Motivating examples include changed camera types and altered agent morphology without retraining or adaptation.Source: Introduction · p. 1
  • Domain generalization trains models to function in new target domains without updating them using target-domain data.Unlike domain adaptation, DG assumes zero training examples from the target problem.Source: Introduction · pp. 1–2

Method

  • MLDG synthesizes virtual training and testing domains within each minibatch and optimizes training performance so its update direction also improves virtual testing loss.The procedure uses meta-optimization to train a base learner for greater domain generality.Source: Introduction · p. 2
  • MLDG is model agnostic, introduces no new parameters, and applies to both supervised and reinforcement learning settings.It does not constrain the architecture of the base learner.Source: Introduction · p. 2

Evaluation

  • The method achieves state-of-the-art results on a recent cross-domain image-recognition benchmark and promising results on two classic reinforcement-learning tasks.The evaluation covers both visual recognition and reinforcement learning.Source: Introduction · p. 2

Related Work

Prior domain-generalization work primarily learns domain-invariant representations by reducing differences among source domains. The paper distinguishes its approach as the first to address domain generalization through meta-learning.

Multi-Domain Learning

  • Multi-domain learning targets one model effective across known domains, whereas domain generalization targets held-out unknown domains.DG often begins with multiple source domains but evaluates generalization beyond them.Source: Related Work · p. 2

Domain Generalization

  • Existing DG methods commonly learn shared representations that minimize source-domain gaps so they can perform well on a new target domain.Examples include multi-view autoencoders, mean map embeddings, and gradient-reversal domain-confusion losses.Source: Related Work · p. 2

Meta-Learning

  • The paper positions MLDG as the first domain-generalization approach based on meta-learning rather than representation-alignment mechanisms.This contrasts with prior methods that seek domain-indistinguishable shared representations.Source: Related Work · p. 2

Methodology

MLDG trains a base learner for domain generalization by simulating train–test domain shifts within each iteration and optimizing performance across virtual domains. Its objective coordinates improvements on meta-train and meta-test domains, while gradient-based variants extend this idea to model-agnostic supervised and reinforcement learning settings.

Meta-Learning Domain Generalization

  • Each iteration splits source domains into meta-train and virtual meta-test sets to mimic real train–test domain shifts.The virtual meta-test domains represent held-out domains during training.Source: Meta-Learning Domain Generalization · pp. 2–3

Supervised Learning

Reinforcement Learning

Analysis of MLDG

  • The meta-optimization objective minimizes meta-train and meta-test losses while encouraging their gradients to point in similar directions.Gradient alignment represents coordinated descent across the two domain sets rather than asymmetric optimization.Source: Analysis of MLDG · p. 4

Alternative Variants of MLDG

  • MLDG-GC normalizes gradients for cosine-similarity regularization, while MLDG-GN uses the intuition that meta-test gradients should approach zero after meta-train convergence.MLDG-GN requires a good initialization and is initialized with the domain aggregation baseline.Source: Alternative Variants of MLDG · p. 4

Experiments

Experiments evaluate MLDG across synthetic classification, PACS cross-domain recognition, and Cart-Pole and Mountain Car reinforcement learning. The results show strong domain-generalization performance, while the benefit of aggregating source domains and MLDG variants depends on the problem.

Experimental settings

PACS ablations

  • ≈2.7% margin over Deep-All is obtained when MLDG is applied to all AlexNet layers rather than using the vanilla baseline.MLDG on fully connected layers provides ≈1.6%, while applying it to convolutional layers adds a further ≈1.1%.Source: Experiment II: Object Recognition · p. 5
  • The meta-optimisation step provides the key benefit: setting α = 0 performs comparably with Deep-All, whereas vanilla MLDG performs best among the evaluated variants.MLDG-GC and MLDG-GN provide some benefit compared with Deep-All, but vanilla MLDG achieves the strongest result in the reported PACS variant comparison.Source: Experiment II: Object Recognition · pp. 5–6

Overall findings

  • MLDG-based meta-learning effectively alleviates domain shift across supervised and reinforcement-learning problems and always outperforms prior alternatives in the reported experiments.The paper reports state-of-the-art results on PACS and promising results on Cart-Pole and Mountain Car, with the core MLDG strategy effective across all problems.Source: Discussion · p. 7
  • Aggregating multiple source domains is problem dependent: it works for PACS and Mountain Car but not for Cart-Pole.The paper also reports mixed results for MLDG-GC and MLDG-GN, with the stronger variant differing across experiments.Source: Discussion · p. 7, Experiment IV: Mountain Car · p. 7

Conclusion

The paper proposes MLDG, a model-agnostic meta-learning procedure for domain generalization, and reports strong results across visual recognition and reinforcement learning.

  • MLDG trains models for domain generalization through meta-optimization on simulated train/test splits with domain shift.Source: Conclusion · p. 7
  • Unlike prior model-based approaches, MLDG scales with the number of domains and can be applied to different base network types.Source: Conclusion · p. 7
  • MLDG applies to both supervised and reinforcement learning problems.Source: Conclusion · p. 7
  • Experiments show state-of-the-art results on a challenging visual recognition benchmark and promising results on multiple classic reinforcement learning problems.Source: Conclusion · p. 7

Related papers

Loading 1710.03463v1…