Improving scDiffusion with Sparsity-Biased Classifier-Free Guidance

• URL: http://arxiv.org/abs/2607.29043v1
• Date: Fri, 31 Jul 2026 05:46:07 GMT
• Title: Improving scDiffusion with Sparsity-Biased Classifier-Free Guidance
• Abstract summary: We propose a sparsity-biased classifier-free guidance (SB-CFG) strategy for scRNA-seq generation.<n>Rather than approximating the assumed "neutral" marginal distribution, SB-CFG introduces a deliberately under-informative sparse reference for the unconditional branch.<n>This "bad" reference amplifies the contrast between conditional and unconditional predictions, leading to stronger and more effective guidance during sampling.
• Score: 13.686193948598897
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Single-cell RNA sequencing (scRNA-seq) has become an essential tool in modern cellular biology, and generating accurate synthetic scRNA-seq data is becoming increasingly important. Although diffusion models have achieved promising results in conditional scRNA-seq generation, existing guidance strategies, including classifier guidance and classifier-free guidance (CFG), rely on an unconditional branch trained to approximate the true marginal distribution, which may retain substantial gene-specific structure and limit guidance effectiveness. Inspired by recent work showing that diffusion models can be effectively guided using intentionally degraded references, we propose a sparsity-biased classifier-free guidance (SB-CFG) strategy for scRNA-seq generation. Rather than approximating the assumed "neutral" marginal distribution, SB-CFG introduces a deliberately under-informative sparse reference for the unconditional branch, removing gene identity while preserving only coarse sparsity statistics. This "bad" reference amplifies the contrast between conditional and unconditional predictions, leading to stronger and more effective guidance during sampling. We evaluated SB-CFG as a training-free sampling modification on five publicly available scRNA-seq datasets. Experimental results demonstrate consistent improvements over standard CFG-based sampling in terms of marker gene expression fidelity, cell-type consistency, and sparsity preservation, indicating that SB-CFG better captures biologically meaningful gene expression patterns.

Related papers

• CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion [20.970593459575756]
  Inferring gene regulatory networks (GRNs) from single-cell transcriptomic data is crucial for biological discovery.<n>We reformulate GRN inference as an inductive, ranking-centric graph completion problem.<n>We introduce textbfbenchmark, a new benchmark that incorporates an inductive gene-holdout split together with knowledge graph completion metrics.
  arXiv  Detail & Related papers  (2026-07-14T16:07:23Z)
• BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks [25.29216866424431]
  We propose an innovative framework named Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks (BRIDGE)<n>BRIDGE extracts gene and cell representations from the expression matrix and its matrix dual, and performs contrastive learning in the gene space and cell space between self and neighbors.<n>It then applies heterogeneous gated encoding to adaptively regulate information transfer between genes and cells, enabling robust transcription factor-to-target gene prediction.
  arXiv  Detail & Related papers  (2026-06-02T11:54:36Z)
• scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement [84.88065404629079]
  scHelix is a dataset-adaptive framework that fundamentally changes how features are processed.<n> scHelix utilizes a dual-stream sparse diffusion encoder equipped with stop-gradient graph caching.<n> scHelix outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-18T15:55:13Z)
• RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq Prediction [48.07329582311906]
  We propose RNA-FM, a flow-matching generative framework for genome-wide bulk RNA-seq prediction from whole-slide images.<n> RNA-FM formulates transcriptomic prediction as a continuous-time conditional transport problem.<n>It enables scalable and biologically interpretable genome-wide gene expression imputation.
  arXiv  Detail & Related papers  (2026-05-12T06:48:58Z)
• Adversarial Domain Adaptation Enables Knowledge Transfer Across Heterogeneous RNA-Seq Datasets [2.0755366440393743]
  Deep learning models have demonstrated strong potential to outperform classical machine learning approaches.<n>In transcriptomics, such datasets are frequently limited, leading to over-fitting and poor generalization.<n>We propose a deep learning-based domain adaptation framework that enables effective knowledge transfer from a large general dataset to a smaller one for cancer type classification.
  arXiv  Detail & Related papers  (2026-03-09T07:55:32Z)
• ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions [64.17845687013434]
  We propose ReDiSC, a structured diffusion model for structured node classification.<n>We show that ReDiSC achieves superior or highly competitive performance compared to state-of-the-art GNN, label propagation, and diffusion-based baselines.<n> Notably, ReDiSC scales effectively to large-scale datasets on which previous structured diffusion methods fail due to computational constraints.
  arXiv  Detail & Related papers  (2025-07-19T04:46:53Z)
• LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations [1.0377683220196872]
  We introduce LapDDPM, a novel conditional Graph Diffusion Probabilistic Model for robust and high-fidelity scRNA-seq generation.<n>Our contributions are threefold: we develop a conditional score-based model for effective learning and generation from complex scRNA-seq distributions.<n>Experiments on diverse scRNA-seq datasets demonstrate LapDDPM's superior performance, achieving high fidelity and generating biologically-plausible, cell-type-specific samples.
  arXiv  Detail & Related papers  (2025-06-16T10:35:32Z)
• Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models [57.20761595019967]
  We present Normalized Attention Guidance (NAG), an efficient, training-free mechanism that applies extrapolation in attention space with L1-based normalization and refinement.<n>NAG restores effective negative guidance where CFG collapses while maintaining fidelity.<n>NAG generalizes across architectures (UNet, DiT), sampling regimes (few-step, multi-step), and modalities (image, video)
  arXiv  Detail & Related papers  (2025-05-27T13:30:46Z)
• Regressor-free Molecule Generation to Support Drug Response Prediction [83.25894107956735]
  Conditional generation based on the target IC50 score can obtain a more effective sampling space. Regressor-free guidance combines a diffusion model's score estimation with a regression controller model's gradient based on number labels.
  arXiv  Detail & Related papers  (2024-05-23T13:22:17Z)
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data [125.7135706352493]
  Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator overfitting. This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator.
  arXiv  Detail & Related papers  (2021-11-12T18:13:45Z)

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.