Identifiable Deep Generative Models via Sparse Decoding

20 October 2021

Papers citing "Identifiable Deep Generative Models via Sparse Decoding"

30 / 30 papers shown

Title
Time-varying Factor Augmented Vector Autoregression with Grouped Sparse Autoencoder Yiyong Luo Brooks Paige Jim Griffin CML 44 0 0 06 Mar 2025
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling Emanuele Marconato Sébastien Lachapelle Sebastian Weichwald Luigi Gresele 64 3 0 30 Oct 2024
LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling Xin Li Anand Sarwate 21 0 0 16 Sep 2024
On the Identifiability of Sparse ICA without Assuming Non-Gaussianity Ignavier Ng Yujia Zheng Xinshuai Dong Kun Zhang CML 32 5 0 19 Aug 2024
Linear causal disentanglement via higher-order cumulants Paula Leyes Carreno Chiara Meroni A. Seigal CML 31 0 0 05 Jul 2024
Marrying Causal Representation Learning with Dynamical Systems for Science Dingling Yao Caroline Muller Francesco Locatello CML AI4CE 40 6 0 22 May 2024
Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning Kyle Hsu Jubayer Ibn Hamid Kaylee Burns Chelsea Finn Jiajun Wu CML 21 4 0 16 Apr 2024
A Sparsity Principle for Partially Observable Causal Representation Learning Danru Xu Dingling Yao Sébastien Lachapelle Perouz Taslakian Julius von Kügelgen Francesco Locatello Sara Magliacane CML 32 13 0 13 Mar 2024
Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models Goutham Rajendran Simon Buchholz Bryon Aragam Bernhard Schölkopf Pradeep Ravikumar AI4CE 83 21 0 14 Feb 2024
Bayesian Transfer Learning Piotr M. Suder Jason Xu David B. Dunson 28 5 0 20 Dec 2023
The Linear Representation Hypothesis and the Geometry of Large Language Models Kiho Park Yo Joong Choe Victor Veitch LLMSV MILM 24 136 0 07 Nov 2023
Object-centric architectures enable efficient causal representation learning Amin Mansouri Jason S. Hartford Yan Zhang Yoshua Bengio CML OCL OOD 21 15 0 29 Oct 2023
Causal Representation Learning Made Identifiable by Grouping of Observational Variables H. Morioka Aapo Hyvarinen OOD CML BDL 25 9 0 24 Oct 2023
Provable Compositional Generalization for Object-Centric Learning Thaddäus Wiedemer Jack Brady Alexander Panfilov Attila Juhos Matthias Bethge Wieland Brendel OCL 27 17 0 09 Oct 2023
Identifying Representations for Intervention Extrapolation Sorawit Saengkyongam Ezgi Ozyilkan Pradeep Ravikumar Niklas Pfister Jonas Peters CML OOD 16 14 0 06 Oct 2023
Learning multi-modal generative models with permutation-invariant encoders and tighter variational bounds Marcel Hirt Domenico Campolo Victoria Leong Juan-Pablo Ortega DRL 8 0 0 01 Sep 2023
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation Sébastien Lachapelle Divyat Mahajan Ioannis Mitliagkas Simon Lacoste-Julien 34 25 0 05 Jul 2023
Conditionally Invariant Representation Learning for Disentangling Cellular Heterogeneity H. Aliee Ferdinand Kapl Soroor Hediyeh-zadeh Fabian J. Theis CML 18 6 0 02 Jul 2023
On the Identifiability of Quantized Factors Vitória Barin Pacela Kartik Ahuja Simon Lacoste-Julien Pascal Vincent OOD CML 15 1 0 28 Jun 2023
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing Simon Buchholz Goutham Rajendran Elan Rosenfeld Bryon Aragam Bernhard Schölkopf Pradeep Ravikumar CML 32 57 0 04 Jun 2023
Nonparametric Identifiability of Causal Representations from Unknown Interventions Julius von Kügelgen M. Besserve Wendong Liang Luigi Gresele Armin Kekić Elias Bareinboim David M. Blei Bernhard Schölkopf CML 16 56 0 01 Jun 2023
Neuro-Causal Factor Analysis Alex Markham Ming-Yu Liu Bryon Aragam Liam Solus CML 18 3 0 31 May 2023
Disentanglement via Latent Quantization Kyle Hsu W. Dorrell James C. R. Whittington Jiajun Wu Chelsea Finn DRL 13 24 0 28 May 2023
Expressive architectures enhance interpretability of dynamics-based neural population models Andrew R. Sedler Chris VerSteeg C. Pandarinath 27 10 0 07 Dec 2022
Linear Causal Disentanglement via Interventions C. Squires A. Seigal Salil Bhate Caroline Uhler CML 13 66 0 29 Nov 2022
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning Sébastien Lachapelle T. Deleu Divyat Mahajan Ioannis Mitliagkas Yoshua Bengio Simon Lacoste-Julien Quentin Bertrand 10 32 0 26 Nov 2022
Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling Romain Lopez Natavsa Tagasovska Stephen Ra K. Cho J. Pritchard Aviv Regev OOD CML DRL 21 35 0 07 Nov 2022
When are Post-hoc Conceptual Explanations Identifiable? Tobias Leemann Michael Kirchhof Yao Rong Enkelejda Kasneci Gjergji Kasneci 50 10 0 28 Jun 2022
Covariate-informed Representation Learning to Prevent Posterior Collapse of iVAE Young-geun Kim Y. Liu Xue Wei OOD CML 20 1 0 09 Feb 2022
Weakly-Supervised Disentanglement Without Compromises Francesco Locatello Ben Poole Gunnar Rätsch Bernhard Schölkopf Olivier Bachem Michael Tschannen CoGe OOD DRL 173 313 0 07 Feb 2020