paper-with-me

홈 › Papers

Leveraging Task Structures for Improved Identifiability in Neural Network Representations

2023-06-26 · Wenlin Chen, Julien Horwood, Juyeon Heo, José Miguel Hernández-Lobato

This work extends the theory of identifiability in supervised learning by considering the consequences of having access to a distribution of tasks. In such cases, we show that linear identifiability is achievable in the general multi-task regression setting. Furthermore, we show that the existence of a task distribution which defines a conditional prior over latent factors reduces the equivalence class for identifiability to permutations and scaling of the true latent factors, a stronger and more useful result than linear identifiability. Crucially, when we further assume a causal structure over these tasks, our approach enables simple maximum marginal likelihood optimization, and suggests potential downstream applications to causal representation learning. Empirically, we find that this straightforward optimization procedure enables our model to outperform more general unsupervised models in recovering canonical representations for both synthetic data and real-world molecular data.

📄 PDF Abstract BibTeX arXiv:2306.14861

Code (1)

jdhorwood/mtlcm 공식 구현 pytorch

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention

2026-03-15 · Markus W. Baumgartner, Anson Lei, Joe Watson, Ingmar Posner arxiv

Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a prede…

Representation Learning

Statistical and structural identifiability in representation learning

2026-03-12 · Walter Nelson, Marco Fumero, Theofanis Karaletsos, Francesco Locatello arxiv

Representation learning models exhibit a surprising stability in their internal representations. Whereas most prior work treats this stability as a single property, we formalize it as two distinct concepts: statistical i…

Representation Learning

Identification of Nonlinear Latent Hierarchical Models

2023-06-13 · NeurIPS 2023 11

Identifying latent variables and causal structures from observational data is essential to many real-world applications involving biological data, medical data, and unstructured data such as images and languages. However…

On the Identifiability of Switching Dynamical Systems

2023-05-25 · Carles Balsells-Rodas, Yixin Wang, Yingzhen Li

The identifiability of latent variable models has received increasing attention due to its relevance in interpretability and out-of-distribution generalisation. In this work, we study the identifiability of Switching Dyn…

Causal DiscoveryTime Series

Identifiable Latent Polynomial Causal Models Through the Lens of Change

2023-10-24 · Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong 외

Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, kn…

Representation Learning