Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning

• URL: http://arxiv.org/abs/2601.20069v1
• Date: Tue, 27 Jan 2026 21:30:21 GMT
• Title: Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
• Authors: Chi-Yao Huang, Khoa Vo, Aayush Atul Verma, Duo Lu, Yezhou Yang,
• Abstract summary: Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations.<n>We introduce Domain Expansion, a framework that prevents these conflicts by restructuring the latent space itself.
• Score: 26.322513515274764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Position: General Alignment Has Hit a Ceiling; Edge Alignment Must Be Taken Seriously [51.03213216886717]
  We take the position that the dominant paradigm of General Alignment reaches a structural ceiling in settings with conflicting values.<n>We introduce Edge Alignment as a distinct approach in which systems preserve multi dimensional value structure.
  arXiv  Detail & Related papers  (2026-02-23T16:51:43Z)
• Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective [55.919842734983156]
  CoSA is a transferable attack framework that operates within a shared low-dimensional semantic space.<n>CoSA consistently outperforms state-of-the-art transferable attacks.
  arXiv  Detail & Related papers  (2026-01-30T15:48:11Z)
• Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning [9.97195966127976]
  Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging.<n>We propose a partition-based multi-stage fine-tuning framework designed to exploit inter-domain synergies while minimizing negative transfer.<n>Our approach strategically partitions domains into subsets (stages) by balancing domain discrepancy, synergy, and model capacity constraints.
  arXiv  Detail & Related papers  (2025-11-10T15:27:26Z)
• Towards Robust and Realistic Human Pose Estimation via WiFi Signals [85.60557095666934]
  WiFi-based human pose estimation is a challenging task that bridges discrete and subtle WiFi signals to human skeletons.<n>This paper revisits this problem and reveals two critical yet overlooked issues: 1) cross-domain gap, i.e., due to significant variations between source-target domain pose distributions; and 2) structural fidelity gap, i.e., predicted skeletal poses manifest distorted topology.<n>This paper fills these gaps by reformulating the task into a novel two-phase framework dubbed DT-Pose: Domain-consistent representation learning and Topology-constrained Pose decoding.
  arXiv  Detail & Related papers  (2025-01-16T09:38:22Z)
• Disentangled Representation Learning with the Gromov-Monge Gap [65.73194652234848]
  Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning.<n>We introduce a novel approach to disentangled representation learning based on quadratic optimal transport.<n>We demonstrate the effectiveness of our approach for quantifying disentanglement across four standard benchmarks.
  arXiv  Detail & Related papers  (2024-07-10T16:51:32Z)
• Latent Functional Maps: a spectral framework for representation alignment [34.20582953800544]
  We introduce a multi-purpose framework to the representation learning community, which allows to: (i) compare different spaces in an interpretable way and measure their intrinsic similarity; (ii) find correspondences between them, both in unsupervised and weakly supervised settings, and (iii) to effectively transfer representations between distinct spaces.<n>We validate our framework on various applications, ranging from stitching to retrieval tasks, and on multiple modalities, demonstrating that Latent Functional Maps can serve as a swiss-army knife for representation alignment.
  arXiv  Detail & Related papers  (2024-06-20T10:43:28Z)
• Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation [14.419786126791369]
  Weakly supervised semantic segmentation (WSSS) with image-level labels aims to achieve segmentation tasks without dense annotations. Co-occurrence problem is widely present and leads to false activation of objects in WSSS. We devise a 'Separate and Conquer' scheme SeCo to tackle this issue from dimensions of image space and feature space.
  arXiv  Detail & Related papers  (2024-02-28T16:43:27Z)
• Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space [45.418113011182186]
  This study proposes a novel method to address limitations by combining Variational AutoEncoders (VAEs) with a Factor Analysis latent space (FA-VAE) The proposed FA-VAE method employs multiple VAEs to learn a private representation for each heterogeneous data view in a continuous latent space.
  arXiv  Detail & Related papers  (2022-07-19T10:46:02Z)
• Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment [130.84010267004803]
  Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. We propose a relaxed spatial structural alignment method to calibrate the target generative models during the adaption.
  arXiv  Detail & Related papers  (2022-03-06T14:26:25Z)
• Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces [0.0]
  This work introduces Design Strategy Network (DSN), a data-driven deep hierarchical framework that learns strategies over arbitrary complex action spaces. The hierarchical architecture decomposes every action decision into first predicting a preferred spatial region in the design space. Results show that DSNs significantly outperform non-hierarchical methods of policy representation.
  arXiv  Detail & Related papers  (2021-10-07T19:29:40Z)
• Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains [108.11746235308046]
  We propose a novel approach that learns domain-agnostic structured latent embeddings by projecting images from different domains. Our experiments on the challenging DomainNet and DomainNet-LS benchmarks show the superiority of our approach over existing methods.
  arXiv  Detail & Related papers  (2021-07-12T17:57:46Z)
• Spatial Attention Pyramid Network for Unsupervised Domain Adaptation [66.75008386980869]
  Unsupervised domain adaptation is critical in various computer vision tasks. We design a new spatial attention pyramid network for unsupervised domain adaptation. Our method performs favorably against the state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2020-03-29T09:03:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.