REVIEW 16 cited by
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks, interpretability, etc. We consider the problem of unsupervised learning of disentangled representations from large pool of unlabeled observations, and propose a variational inference based approach to infer disentangled latent factors. We introduce a regularizer on the expectation of the approximate posterior over observed data that encourages the disentanglement. We also propose a new disentanglement metric which is better aligned with the qualitative disentanglement observed in the decoder's output. We empirically observe significant improvement over existing methods in terms of both disentanglement and data likelihood (reconstruction quality).
Forward citations
Cited by 16 Pith papers
-
Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability
Enforcing local orthogonality on the Jacobian of the generative mapping yields identifiability for general nonlinear models when the latent domain has full combinatorial support.
-
Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias
MKAN adds hard unconstrained monotonicity to KANs via reparameterization and proves a size bound of at most 2N* for monotone equivalents of ball-partition feature extractors.
-
Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
An ISA-style Lp-nested prior over VAE latents improves disentanglement and reduces the reconstruction/regularization trade-off compared to modified-ELBO methods like beta-VAE.
-
MB-Loc: Multi-planar Bird's-eye-view Localization in outdoor LiDAR scenes
MB-Loc projects LiDAR point clouds into multi-planar BEV images, applies 2D CNNs with a KL-regularized latent bottleneck and 3D augmentations, and reports real-time state-of-the-art localization accuracy on the NCLT dataset.
-
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phase...
-
Causal Representation Learning from Network Data
GRACE-VAE couples a graph neural network encoder with a causal discrepancy VAE decoder so that known pathway and protein networks improve learning of latent causal programs and prediction of CRISPR perturbation effects.
-
Theory and Evaluation Metrics for Learning Disentangled Representations
New information-theoretic metrics (RMIG, JEMMIG, WSEPIN) rank disentanglement models consistently, but they are sensitive to quantization choices and high latent dimensionality.
-
Geometric Disentanglement for Generative Latent Shape Models
An unsupervised VAE for 3D point clouds is structured so that latent variables separately control intrinsic shape and extrinsic pose, using Laplace-Beltrami spectra and hierarchical disentanglement penalties.
-
Decafs: Disentangled Conditional adversarial Flows
Decaf trains a Lie-group generator whose disentangled latent space is aligned with a normalizing flow's latent space, so that changing one learned coordinate changes one generative factor.
-
Unveiling and Steering Connectome Organization with Interpretable Latent Variables
A VAE with SHAP-based interpretability learns low-dimensional codes for Drosophila connectome subgraphs, and the codes can be steered to generate graph subgraphs with targeted edge counts and other properties.
-
Disentanglement in Difference: Directly Learning Semantically Disentangled Representations by Maximizing Inter-Factor Differences
DiD uses a GAN with a difference encoder that maximizes distances between image-change vectors from different latent axes, reporting improved disentanglement metrics on dSprites and 3DShapes.
-
Improving Disentangled Representation Learning with the Beta Bernoulli Process
A VAE with a Beta-Bernoulli process (Indian Buffet Process) prior achieves better disentanglement and reconstruction than Gaussian-prior VAEs on several benchmarks and improves supervised clinical tasks when combined ...
-
Fractal Flow: Hierarchical and Interpretable Normalizing Flow via Topic Modeling and Recursive Strategy
Fractal Flow combines a Dirichlet-topic latent prior with recursive coupling layers in a normalizing flow, reporting lower bits-per-dim than a custom RealNVP baseline on MNIST and FashionMNIST.
-
Unsupervised Region-Based Image Editing of Denoising Diffusion Models
A masking and Jacobian projection technique discovers unsupervised semantic directions in diffusion model latent space, enabling region-local editing without fine-tuning.
-
Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
A V-shaped pattern in the training objective of factorized VAEs is attributed to a tunable 'disentangling granularity', but the effect is confounded because coarser granularity removes penalty terms by construction.
-
PH-VAE: A Polynomial Hierarchical Variational Autoencoder Towards Disentangled Representation Learning
A VAE variant that uses polynomial powers of the input as separate encoder streams and an averaged KL loss is claimed to improve reconstruction and disentanglement, but the mathematical derivation and experiments do n...
Discussion (0). Continue with ORCID to comment.