Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations

• URL: http://arxiv.org/abs/2607.16725v1
• Date: Sat, 18 Jul 2026 09:21:53 GMT
• Title: Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations
• Abstract summary: We propose a semi-supervised framework combining conditional intrinsic with low-dimensional latent representations.<n>RepG decomposes generation into two stages: label-dependent latent sampling and high-dimensional reconstruction.
• Score: 12.299177496689621
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant. To effectively leverage structural information embedded within the unlabeled dataset and compensate for sparse conditioning signals, we propose a semi-supervised framework combining conditional stochastic interpolation with low-dimensional latent representations. RepG decomposes generation into two stages: label-dependent latent sampling and high-dimensional reconstruction. This isolates the supervised learning of conditional dependencies to a low-dimensional space, requiring few labels while utilizing the abundant unlabeled data purely for reconstruction. Theoretically, we establish an error decomposition showing that the Kullback-Leibler divergence of RepG comprises stage-wise estimation errors and a structural bias quantified by conditional mutual information. For deep neural network estimators, we derive non-asymptotic convergence rates proving that RepG significantly improves sample complexity. By confining the supervised estimation burden to the low intrinsic dimension of the latent representation, RepG achieves a strictly faster convergence rate. Complemented by a minimax lower bound, our theoretical results demonstrate that this method effectively mitigates the curse of dimensionality inherent in direct ambient-space generative modeling.

Related papers

• Cluster-Based Dimensionality Reduction by Nonparametric Distributional Screening [1.4773309126683776]
  We consider dimensionality reduction for high-dimensional observations accompanied by a supplied partition into two or more clusters.<n>The proposed procedure compares the cluster-specific empirical distribution functions through a several-sample Kolmogorov-Smirnov separation statistic.<n>We formalize the resulting marginal cluster support and establish simultaneous finite-sample concentration over all coordinates.
  arXiv  Detail & Related papers  (2026-09-06T21:58:59Z)
• Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine [60.669081685261965]
  Diffusion models generate high-dimensional data with remarkable quality.<n>How their training efficiently learns the score function remains theoretically unexplained.<n>We instantiate this principle as Score-induced Latent Diffusion (SiLD)
  arXiv  Detail & Related papers  (2026-05-16T16:51:10Z)
• SEED: Targeted Data Selection by Weighted Independent Set [76.68391670109433]
  We develop a robust and scalable data selection pipeline dubbed SEED.<n>SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-05-15T07:26:54Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• Geometrically Constrained Outlier Synthesis [4.254099382808598]
  Deep neural networks for image classification often exhibit overconfidence on out-of-distribution (OOD) samples.<n>We introduce Geometrically Constrained Outlier Synthesis (GCOS), a training-time regularization framework.<n>The framework naturally transitions to conformal OOD inference, which translates uncertainty scores into statistically valid p-values.
  arXiv  Detail & Related papers  (2026-03-09T14:11:47Z)
• Robust low-rank estimation with multiple binary responses using pairwise AUC loss [0.0]
  Multiple binary responses arise in many modern data-analytic problems.<n>Low-rank models offer a natural way to encode latent dependence across tasks.<n>Existing methods for binary data are largely likelihood-based and focus on pointwise classification.
  arXiv  Detail & Related papers  (2026-01-13T15:00:10Z)
• SIGMA: Scalable Spectral Insights for LLM Collapse [51.863164847253366]
  We introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework for model collapse.<n>By utilizing benchmarks that deriving and deterministic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space.<n>We demonstrate that SIGMA effectively captures the transition towards states, offering both theoretical insights into the mechanics of collapse.
  arXiv  Detail & Related papers  (2026-01-06T19:47:11Z)
• Modes of Sequence Models and Learning Coefficients [0.6906005491572401]
  We develop a geometric account of sequence modelling that links patterns in the data to measurable properties of the loss landscape in transformer networks.<n>We show theoretically that Local Learning Coefficient estimates are insensitive to modes below a data-dependent threshold.<n>This insight clarifies why reliable LLC estimates can be obtained even when a network parameter is not a strict minimiser of the population loss.
  arXiv  Detail & Related papers  (2025-04-25T03:38:10Z)
• TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces [10.86297454943578]
  We present a semi-supervised fine-tuning framework to address the challenges of training for a limited amount of labelled data.<n> Experiments on several datasets demonstrate significant improvements in classification tasks under extremely low-labelled conditions.
  arXiv  Detail & Related papers  (2025-03-10T20:56:54Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling [77.15766509677348]
  Conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to another latent attribute. We propose a general two-step strategy to mitigate this issue.
  arXiv  Detail & Related papers  (2022-12-05T08:09:33Z)
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment [52.02794488304448]
  We propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.
  arXiv  Detail & Related papers  (2020-03-26T22:10:04Z)

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.