从任务出发设计离散表示，让模型学得更实用。
Task-Driven Discrete Representation Learning
- 以下游任务效果为标准，重新定义离散表示好坏
- 理论分析了表征能力与样本复杂度的权衡关系
- 适用于多种任务，兼顾生成与非生成场景
近年来，深度离散表示学习（DRL）在多个领域取得显著进展。现有大多数DRL框架（如广泛使用的VQ-VAE及其变体）主要聚焦于生成设置，表示质量通常通过生成结果的保真度间接衡量。然而，学术界对离散表示的优劣仍缺乏清晰定义。本文从任务驱动视角出发，提出统一框架，评估离散特征在下游任务中的实用性，生成自然成为其中一种可能应用。在此背景下，离散表示的特性及其对特定任务的增益机制仍研究不足。为此，我们进一步提供理论分析，揭示表示容量与样本复杂度之间的权衡，阐明离散表示使用如何影响任务性能。最后，我们在多样应用中验证了该框架的灵活性与有效性。
原文摘要 · Abstract (English)
In recent years, deep discrete representation learning (DRL) has achieved significant success across various domains. Most DRL frameworks (e.g., the widely used VQ-VAE and its variants) have primarily focused on generative settings, where the quality of a representation is implicitly gauged by the fidelity of its generation. In fact, the goodness of a discrete representation remain ambiguously defined across the literature. In this work, we adopt a practical approach that examines DRL from a task-driven perspective. We propose a unified framework that explores the usefulness of discrete features in relation to downstream tasks, with generation naturally viewed as one possible application. In this context, the properties of discrete representations as well as the way they benefit certain tasks are also relatively understudied. We therefore provide an additional theoretical analysis of the trade-off between representational capacity and sample complexity, shedding light on how discrete representation utilization impacts task performance. Finally, we demonstrate the flexibility and effectiveness of our framework across diverse applications.
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。