通过正交子空间重构，解决多任务学习中表征冲突问题。
Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
- 用正交池化机制构建各任务互不干扰的潜在空间。
- 在多个数据集上实现无退化的多任务性能，提升显著。
- 适合需要可解释、可组合表征的多任务研究者。
单一网络训练多个目标常导致梯度冲突，使共享表征退化为对任何任务均次优的折中状态——我们称之为潜在表示坍塌。本文提出领域扩展（Domain Expansion）框架，通过重构潜在空间本身来避免此类冲突。该框架采用新颖的正交池化机制，为每个任务分配相互正交的子空间。我们在多种基准测试（包括ShapeNet、MPIIGaze和旋转MNIST）上验证了该方法，在结合分类与姿态、注视估计的复杂多目标任务中表现出色。实验表明，该结构不仅防止坍塌，还生成了显式、可解释且可组合的潜在空间，支持概念直接操控。
原文摘要 · Abstract (English)
Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptimal for any single task--a problem we term latent representation collapse. We introduce Domain Expansion, a framework that prevents these conflicts by restructuring the latent space itself. Our framework uses a novel orthogonal pooling mechanism to construct a latent space where each objective is assigned to a mutually orthogonal subspace. We validate our approach across diverse benchmarks--including ShapeNet, MPIIGaze, and Rotated MNIST--on challenging multi-objective problems combining classification with pose and gaze estimation. Our experiments demonstrate that this structure not only prevents collapse but also yields an explicit, interpretable, and compositional latent space where concepts can be directly manipulated.
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。