提出高效评估框架与新模型，显著提升组合泛化能力。
Scalable Evaluation and Neural Models for Compositional Generalization
- 构建统一评估框架，计算量从组合级降为常数级
- 在5000+模型上验证，新模型准确率提升23.43%
- 新模型参数开销仅16%，适合大规模应用
组合泛化是现代机器学习的关键挑战，要求模型能预测已知概念的未知组合。然而，当前评估缺乏标准化协议，现有基准往往重效率轻严谨性。同时，通用视觉架构缺少必要归纳偏置，现有增强方法又牺牲可扩展性。为此，本文提出：1）统一并扩展先前方法的严格评估框架，将计算需求从组合级降至常数级；2）对监督视觉主干网络的组合泛化现状进行大规模评估，训练超过5000个模型；3）提出属性不变网络（Attribute Invariant Networks），在组合泛化上达到新帕累托前沿，相比基线提升23.43%准确率，参数开销从600%降至16%。代码已开源。
原文摘要 · Abstract (English)
Compositional generalization-a key open challenge in modern machine learning-requires models to predict unknown combinations of known concepts. However, assessing compositional generalization remains a fundamental challenge due to the lack of standardized evaluation protocols and the limitations of current benchmarks, which often favor efficiency over rigor. At the same time, general-purpose vision architectures lack the necessary inductive biases, and existing approaches to endow them compromise scalability. As a remedy, this paper introduces: 1) a rigorous evaluation framework that unifies and extends previous approaches while reducing computational requirements from combinatorial to constant; 2) an extensive and modern evaluation on the status of compositional generalization in supervised vision backbones, training more than 5000 models; 3) Attribute Invariant Networks, a class of models establishing a new Pareto frontier in compositional generalization, achieving a 23.43% accuracy improvement over baselines while reducing parameter overhead from 600% to 16% compared to fully disentangled counterparts. Our code is available at https://github.com/IBM/scalable-compositional-generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。