XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision

• URL: http://arxiv.org/abs/2601.21688v1
• Date: Thu, 29 Jan 2026 13:20:48 GMT
• Title: XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision
• Abstract summary: textscXFactors is a weakly-supervised VAE framework that disentangles and provides explicit control over a chosen set of factors.<n>We show that our method scales correctly with increasing latent capacity and evaluate it on the real-world dataset CelebA.
• Score: 37.140199946294565
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Disentangled representation learning aims to map independent factors of variation to independent representation components. On one hand, purely unsupervised approaches have proven successful on fully disentangled synthetic data, but fail to recover semantic factors from real data without strong inductive biases. On the other hand, supervised approaches are unstable and hard to scale to large attribute sets because they rely on adversarial objectives or auxiliary classifiers. We introduce \textsc{XFactors}, a weakly-supervised VAE framework that disentangles and provides explicit control over a chosen set of factors. Building on the Disentangled Information Bottleneck perspective, we decompose the representation into a residual subspace $\mathcal{S}$ and factor-specific subspaces $\mathcal{T}_1,\ldots,\mathcal{T}_K$ and a residual subspace $\mathcal{S}$. Each target factor is encoded in its assigned $\mathcal{T}_i$ through contrastive supervision: an InfoNCE loss pulls together latents sharing the same factor value and pushes apart mismatched pairs. In parallel, KL regularization imposes a Gaussian structure on both $\mathcal{S}$ and the aggregated factor subspaces, organizing the geometry without additional supervision for non-targeted factors and avoiding adversarial training and classifiers. Across multiple datasets, with constant hyperparameters, \textsc{XFactors} achieves state-of-the-art disentanglement scores and yields consistent qualitative factor alignment in the corresponding subspaces, enabling controlled factor swapping via latent replacement. We further demonstrate that our method scales correctly with increasing latent capacity and evaluate it on the real-world dataset CelebA. Our code is available at \href{https://github.com/ICML26-anon/XFactors}{github.com/ICML26-anon/XFactors}.

Related papers

• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• Beyond Additive Decompositions: Interpretability Through Separability [1.92520187564634]
  Interpretable machine learning requires models that are accurate and structurally faithful to the data.<n>We propose Separation Learning (TSL), a regression model that learns a sum of rank-1 products of uni-feature functions via a stagewise greedy procedure with refitting.<n>We establish approximation-rate guarantees for functions with bounded mixed $p$-th order partial derivatives and demonstrate that TSL competes with black-box models on regression benchmarks.
  arXiv  Detail & Related papers  (2026-05-29T12:08:14Z)
• Weight-Informed Self-Explaining Clustering for Mixed-Type Tabular Data [63.62853416081748]
  WISE is a framework that unifies representation, feature weighting, clustering, and interpretation.<n>It produces faithful, human-interpretable explanations grounded in the same primitives that drive clustering.
  arXiv  Detail & Related papers  (2026-04-07T13:18:31Z)
• Federated Learning Resilient to Byzantine Attacks and Data Heterogeneity [59.17297282373628]
  This paper addresses Gradient learning (FL) in the context of malicious attacks on data.<n>We introduce a novel Average Robust Algorithm (RAGA) which uses the median for both convergence analysis and loss functions.
  arXiv  Detail & Related papers  (2024-03-20T08:15:08Z)
• Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback [26.935057415769876]
  Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks.<n>We propose a textbfCL-Disentanglement approach dubbed textbfCL-Dis.<n>Experiments demonstrate the superiority of CL-Dis on applications like real image manipulation and visual analysis.
  arXiv  Detail & Related papers  (2024-02-04T05:03:22Z)
• Sanitized Clustering against Confounding Bias [38.928080236294775]
  This paper presents a new clustering framework named Sanitized Clustering Against confounding Bias (SCAB) SCAB removes the confounding factor in the semantic latent space of complex data through a non-linear dependence measure. Experiments on complex datasets demonstrate that our SCAB achieves a significant gain in clustering performance.
  arXiv  Detail & Related papers  (2023-11-02T14:10:14Z)
• Multifactor Sequential Disentanglement via Structured Koopman Autoencoders [2.7759072740347017]
  We consider multifactor disentanglement in which multiple semantic disentangled components are generated. Key to our approach is a strong inductive bias where we assume that the underlying dynamics can be represented linearly in the latent space. We propose a simple and easy to code new deep model that is fully unsupervised and it supports multifactor disentanglement.
  arXiv  Detail & Related papers  (2023-03-30T10:01:58Z)
• FeDXL: Provable Federated Learning for Deep X-Risk Optimization [105.17383135458897]
  We tackle a novel federated learning (FL) problem for optimizing a family of X-risks, to which no existing algorithms are applicable. The challenges for designing an FL algorithm for X-risks lie in the non-decomability of the objective over multiple machines and the interdependency between different machines.
  arXiv  Detail & Related papers  (2022-10-26T00:23:36Z)
• DOT-VAE: Disentangling One Factor at a Time [1.6114012813668934]
  We propose a novel framework which augments the latent space of a Variational Autoencoders with a disentangled space and is trained using a Wake-Sleep-inspired two-step algorithm for unsupervised disentanglement. Our network learns to disentangle interpretable, independent factors from the data one at a time", and encode it in different dimensions of the disentangled latent space, while making no prior assumptions about the number of factors or their joint distribution.
  arXiv  Detail & Related papers  (2022-10-19T22:53:02Z)
• Disentanglement of Correlated Factors via Hausdorff Factorized Support [53.23740352226391]
  We propose a relaxed disentanglement criterion - the Hausdorff Factorized Support (HFS) criterion - that encourages a factorized support, rather than a factorial distribution. We show that the use of HFS consistently facilitates disentanglement and recovery of ground-truth factors across a variety of correlation settings and benchmarks.
  arXiv  Detail & Related papers  (2022-10-13T20:46:42Z)
• Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
  We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
  arXiv  Detail & Related papers  (2021-06-14T05:39:09Z)
• Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement [59.033559925639075]
  We propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction. The corresponding model inductive bias is introduced by our proposed C-S disentanglement Module (C-S DisMo) Experiments on several popular datasets demonstrate that our method achieves the state-of-the-art unsupervised C-S disentanglement.
  arXiv  Detail & Related papers  (2021-02-21T08:04:33Z)

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.