Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment

• URL: http://arxiv.org/abs/2511.22345v2
• Date: Thu, 04 Dec 2025 15:44:45 GMT
• Title: Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
• Authors: Yang Chen, Xiaowei Xu, Shuai Wang, Chenhui Zhu, Ruxue Wen, Xubin Li, Tiezheng Ge, Limin Wang,
• Abstract summary: We propose a novel alignment strategy for Normalizing Flows (NFs)<n>Instead of regularizing the forward pass, we align the intermediate features of the generative (reverse) pass with representations from a powerful vision foundation model.<n>We also introduce a novel training-free, test-time optimization algorithm for classification, which provides a more intrinsic evaluation of the NF's embedded semantic knowledge.
• Score: 27.988711627938276
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new samples from this space. This characteristic creates an intrinsic synergy between representation learning and data generation. However, the generative quality of standard NFs is limited by poor semantic representations from log-likelihood optimization. To remedy this, we propose a novel alignment strategy that creatively leverages the invertibility of NFs: instead of regularizing the forward pass, we align the intermediate features of the generative (reverse) pass with representations from a powerful vision foundation model, demonstrating superior effectiveness over naive alignment. We also introduce a novel training-free, test-time optimization algorithm for classification, which provides a more intrinsic evaluation of the NF's embedded semantic knowledge. Comprehensive experiments demonstrate that our approach accelerates the training of NFs by over 3.3$\times$, while simultaneously delivering significant improvements in both generative quality and classification accuracy. New state-of-the-art results for NFs are established on ImageNet 64$\times$64 and 256$\times$256. Our code is available at https://github.com/MCG-NJU/FlowBack.

Related papers

• Self-Supervised Learning via Flow-Guided Neural Operator on Time-Series Data [57.85958428020496]
  Flow-Guided Neural Operator (FGNO) is a novel framework combining operator learning with flow matching for SSL training.<n>FGNO learns mappings in functional spaces by using Short-Time Fourier Transform to unify different time resolutions.<n>Unlike prior generative SSL methods that use noisy inputs during inference, we propose using clean inputs for representation extraction while learning representations with noise.
  arXiv  Detail & Related papers  (2026-02-12T18:54:57Z)
• DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation [47.409626500688866]
  We present the DINO Spherical Autoencoder (DINO-SAE), a framework that bridges semantic representation and pixel-level reconstruction.<n>Our approach achieves state-of-the-art reconstruction quality, reaching 0.37 rFID and 26.2 dB PSNR, while maintaining strong semantic alignment to the pretrained VFM.
  arXiv  Detail & Related papers  (2026-01-30T12:25:34Z)
• Bidirectional Normalizing Flow: From Data to Noise and Back [16.352742402707953]
  Normalizing Flows (NFs) have been established as a principled framework for generative modeling.<n>Recent developments in TARFlow and its variants have revitalized NF methods by combining Transformers and autoregressive flows.<n>We introduce BiFlow, a framework that removes the need for an exact analytic inverse.
  arXiv  Detail & Related papers  (2025-12-11T18:59:55Z)
• A Constructive Framework for Nondeterministic Automata via Time-Shared, Depth-Unrolled Feedforward Networks [0.0]
  We present a formal and constructive simulation framework for nondeterministic finite automata (NFAs) using time-shared, depth-unrolled feedforward networks (TS-FFNs)<n>Our formulation symbolically encodes automaton states as binary vectors, transitions as sparse matrix transformations, and nondeterministic branching-including $varepsilon$-closures-as compositions of shared thresholded updates.
  arXiv  Detail & Related papers  (2025-05-30T01:18:35Z)
• Latent Bayesian Optimization via Autoregressive Normalizing Flows [17.063294409131238]
  We propose a Normalizing Flow-based Bayesian Optimization (NF-BO) to solve the value discrepancy problem.<n>Our method demonstrates superior performance in molecule generation tasks, significantly outperforming both traditional and recent LBO approaches.
  arXiv  Detail & Related papers  (2025-04-21T06:36:09Z)
• Accelerating Full Waveform Inversion By Transfer Learning [1.0881446298284452]
  Full waveform inversion (FWI) is a powerful tool for reconstructing material fields based on sparsely measured data obtained by wave propagation. For specific problems, discretizing the material field with a neural network (NN) improves the robustness and reconstruction quality of the corresponding optimization problem. In this paper, we introduce a novel transfer learning approach to further improve NN-based FWI.
  arXiv  Detail & Related papers  (2024-08-01T16:39:06Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• On the Initialization of Graph Neural Networks [10.153841274798829]
  We analyze the variance of forward and backward propagation across Graph Neural Networks layers. We propose a new method for Variance Instability Reduction within GNN Optimization (Virgo) We conduct comprehensive experiments on 15 datasets to show that Virgo can lead to superior model performance.
  arXiv  Detail & Related papers  (2023-12-05T09:55:49Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• Taming Hyperparameter Tuning in Continuous Normalizing Flows Using the JKO Scheme [60.79981399724534]
  A normalizing flow (NF) is a mapping that transforms a chosen probability distribution to a normal distribution. We present JKO-Flow, an algorithm to solve OT-based CNF without the need of tuning $alpha$.
  arXiv  Detail & Related papers  (2022-11-30T05:53:21Z)
• Invertible Neural Networks for Graph Prediction [22.140275054568985]
  In this work, we address conditional generation using deep invertible neural networks. We adopt an end-to-end training approach since our objective is to address prediction and generation in the forward and backward processes at once.
  arXiv  Detail & Related papers  (2022-06-02T17:28:33Z)
• Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification [69.26747803963907]
  Rank-R Feedforward Neural Network (FNN) is a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters. First, it handles inputs as multilinear arrays, bypassing the need for vectorization, and can thus fully exploit the structural information along every data dimension. We establish the universal approximation and learnability properties of Rank-R FNN, and we validate its performance on real-world hyperspectral datasets.
  arXiv  Detail & Related papers  (2021-04-11T16:37:32Z)
• Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow [83.27681781274406]
  Generalized zero-shot learning aims to recognize both seen and unseen classes by transferring knowledge from semantic descriptions to visual representations. Recent generative methods formulate GZSL as a missing data problem, which mainly adopts GANs or VAEs to generate visual features for unseen classes. We propose a conditional version of generative flows for GZSL, i.e., VAE-Conditioned Generative Flow (VAE-cFlow)
  arXiv  Detail & Related papers  (2020-09-01T09:12:31Z)

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.