Imagen de Portada

Mechanistic Independence: A Principle for Identifiable Disentangled Representations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Matthes, Stefan, Han, Zhiwei, Shen, Hao
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors
por: Han, Zhiwei, et al.
Publicado: (2025)

Provable Subspace Identification of Nonlinear Multi-view CCA
por: Han, Zhiwei, et al.
Publicado: (2026)

Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms
por: Komanduri, Aneesh, et al.
Publicado: (2023)

Independence Constrained Disentangled Representation Learning from Epistemological Perspective
por: Wang, Ruoyu, et al.
Publicado: (2024)

Physics-Informed Learning of Flow Distribution and Receiver Heat Losses in Parabolic Trough Solar Fields
por: Matthes, Stefan, et al.
Publicado: (2025)

Disentangled Representation Learning via Flow Matching
por: Chi, Jinjin, et al.
Publicado: (2026)

Linear Causal Representation Learning by Topological Ordering, Pruning, and Disentanglement
por: Chen, Hao, et al.
Publicado: (2025)

Disentanglement as Identifiable Pushforward Factorisation
por: Allen, Carl
Publicado: (2024)

MeGU: Machine-Guided Unlearning with Target Feature Disentanglement
por: Wang, Haoyu, et al.
Publicado: (2026)

Variational Learning of Disentangled Representations
por: Slavutsky, Yuli, et al.
Publicado: (2025)

Efficiently Disentangle Causal Representations
por: Li, Yuanpeng, et al.
Publicado: (2022)

Continual Learning of Nonlinear Independent Representations
por: Sun, Boyang, et al.
Publicado: (2024)

From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
por: Cai, Ruichu, et al.
Publicado: (2024)

On the Identifiability of Causal Graphs with the Invariance Principle
por: Montagna, Francesco
Publicado: (2025)

Disentangled Representation Learning
por: Wang, Xin, et al.
Publicado: (2022)

Learning Representations for Independence Testing
por: Xu, Nathaniel, et al.
Publicado: (2024)

Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target
por: Zhao, Jiajie, et al.
Publicado: (2024)

Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
por: Welch, Ryan, et al.
Publicado: (2024)

Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis
por: Su, Jiayu, et al.
Publicado: (2024)

Disentangling Uncertainties by Learning Compressed Data Representation
por: An, Zhiyu, et al.
Publicado: (2025)

Disentangled Hyperbolic Representation Learning for Heterogeneous Graphs
por: Bai, Qijie, et al.
Publicado: (2024)

Challenges in Mechanistically Interpreting Model Representations
por: Golechha, Satvik, et al.
Publicado: (2024)

Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
por: Gao, Weibo, et al.
Publicado: (2024)

CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
por: Rodriguez, Esther, et al.
Publicado: (2025)

Disentangled Representation Learning for Parametric Partial Differential Equations
por: Liu, Ning, et al.
Publicado: (2024)

Temporally Disentangled Representation Learning under Unknown Nonstationarity
por: Song, Xiangchen, et al.
Publicado: (2023)

Towards Identifiability of Hierarchical Temporal Causal Representation Learning
por: Li, Zijian, et al.
Publicado: (2025)

Disentangled Generative Graph Representation Learning
por: Hu, Xinyue, et al.
Publicado: (2024)

SDE: A Simplified and Disentangled Dependency Encoding Framework for State Space Models in Time Series Forecasting
por: Weng, Zixuan, et al.
Publicado: (2024)

Sequential Recommendation with Controllable Diversification: Representation Degeneration and Diversity
por: Fan, Ziwei, et al.
Publicado: (2023)

Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment?
por: Yang, Hongzheng, et al.
Publicado: (2025)

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
por: Méloux, Maxime, et al.
Publicado: (2025)

Learning Disentangled Speech Representations
por: Brima, Yusuf, et al.
Publicado: (2023)

Disentangled Representations for Causal Cognition
por: Torresan, Filippo, et al.
Publicado: (2024)

The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
por: Sutter, Denis, et al.
Publicado: (2025)

Exploring Grokking: Experimental and Mechanistic Investigations
por: Qiye, Hu, et al.
Publicado: (2024)

Biologically Disentangled Multi-Omic Modeling Reveals Mechanistic Insights into Pan-Cancer Immunotherapy Resistance
por: Tariq, Ifrah, et al.
Publicado: (2025)

Disentanglement in Difference: Directly Learning Semantically Disentangled Representations by Maximizing Inter-Factor Differences
por: Zhang, Xingshen, et al.
Publicado: (2025)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
por: Liu, Chenruo, et al.
Publicado: (2025)

Disentangling the Roles of Representation and Selection in Data Pruning
por: Du, Yupei, et al.
Publicado: (2025)