A Domain Generalization Perspective on Listwise Context Modeling

A Game-Theoretic Perspective of Generalization in Reinforcement Learning

Generalization in reinforcement learning (RL) is of importance for real deployment of RL algorithms. Various schemes are proposed to address the generalization issues, including transfer learning, multi-task learning and meta learning, as well as the robust and adversarial reinforcement learning. However, there is not a unified formulation of the various schemes, as well as the comprehensive comparisons of methods across different schemes. In this work, we propose a game-theoretic framework for the generalization in reinforcement learning, named GiRL, where an RL agent is trained against an ad…

冻结过参数化：深度神经网络迁移学习的双下降视角

Frozen Overparameterization: A Double Descent Perspective on Transfer Learning of Deep Neural Networks

该研究从过参数化与双下降视角出发，探究源/目标数据集规模、冻结层数量、任务相似度对DNN迁移学习泛化的影响，通过图像分类实验验证了冻结相关双下降现象等结论。

统一常见域泛化方法的因果框架

A Causal Framework to Unify Common Domain Generalization Approaches

本文提出一个因果框架，从关键思想、理论依据、方法关联及优劣局限三方面统一理解常见域泛化方法，以揭示底层原理并促进更有效方法的开发。

A Combinatorial Perspective on Transfer Learning

Human intelligence is characterized not only by the capacity to learn complex skills, but the ability to rapidly adapt and acquire new skills within an ever-changing environment. In this work we study how the learning of modular solutions can allow for effective generalization to both unseen and potentially differently distributed data. Our main postulate is that the combination of task segmentation, modular learning and memory-based ensembling can give rise to generalization on an exponentially growing number of unseen tasks. We provide a concrete instantiation of this idea using a combinatio…

Domain Generalization using Ensemble Learning

Domain generalization is a sub-field of transfer learning that aims at bridging the gap between two different domains in the absence of any knowledge about the target domain. Our approach tackles the problem of a model's weak generalization when it is trained on a single source domain. From this perspective, we build an ensemble model on top of base deep learning models trained on a single source to enhance the generalization of their collective prediction. The results achieved thus far have demonstrated promising improvements of the ensemble over any of its base learners.

Super-model ecosystem: A domain-adaptation perspective

This paper attempts to establish the theoretical foundation for the emerging super-model paradigm via domain adaptation, where one first trains a very large-scale model, {\it i.e.}, super model (or foundation model in some other papers), on a large amount of data and then adapts it to various specific domains. Super-model paradigms help reduce computational and data cost and carbon emission, which is critical to AI industry, especially enormous small and medium-sized enterprises. We model the super-model paradigm as a two-stage diffusion process: (1) in the pre-training stage, the model parame…

时机至关重要：数据排列影响指令微调中的零样本泛化

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning

本文从数据排列角度研究指令微调中的零样本泛化机制，证明泛化发生在训练早期且损失可作指标，并提出以测试为中心的多轮排列框架来提升持续学习效果。

On Compositional Generalization of Neural Machine Translation

Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks such as WMT. However, there still exist significant issues such as robustness, domain generalization, etc. In this paper, we study NMT models from the perspective of compositional generalization by building a benchmark dataset, CoGnition, consisting of 216k clean and consistent sentence pairs. We quantitatively analyze effects of various factors using compound translation error rate, then demonstrate that the NMT model fails badly on compositional generalization, although it performs rem…