S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain

• URL: http://arxiv.org/abs/2501.00384v1
• Date: Tue, 31 Dec 2024 10:54:41 GMT
• Title: S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain
• Authors: Rui Xia, Yanhua Cheng, Yongxiang Tang, Xiaocheng Liu, Xialong Liu, Lisong Wang, Peng Jiang,
• Abstract summary: We propose S-Diff, inspired by graph-based collaborative filtering. S-Diff maps user interaction vectors into the spectral domain and parameterizes diffusion noise to align with graph frequency. This anisotropic diffusion retains significant low-frequency components, preserving a high signal-to-noise ratio.
• Score: 23.22881271027173
• License:
• Abstract: Recovering user preferences from user-item interaction matrices is a key challenge in recommender systems. While diffusion models can sample and reconstruct preferences from latent distributions, they often fail to capture similar users' collective preferences effectively. Additionally, latent variables degrade into pure Gaussian noise during the forward process, lowering the signal-to-noise ratio, which in turn degrades performance. To address this, we propose S-Diff, inspired by graph-based collaborative filtering, better to utilize low-frequency components in the graph spectral domain. S-Diff maps user interaction vectors into the spectral domain and parameterizes diffusion noise to align with graph frequency. This anisotropic diffusion retains significant low-frequency components, preserving a high signal-to-noise ratio. S-Diff further employs a conditional denoising network to encode user interactions, recovering true preferences from noisy data. This method achieves strong results across multiple datasets.

Related papers

• Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphs [60.82508765185161]
  We propose Dual-Frequency Filtering Self-aware Graph Neural Networks (DFGNN) DFGNN integrates low-pass and high-pass filters to extract smooth and detailed topological features. It dynamically adjusts filtering ratios to accommodate both homophilic and heterophilic graphs.
  arXiv  Detail & Related papers  (2024-11-18T04:57:05Z)
• Frequency-aware Feature Fusion for Dense Image Prediction [99.85757278772262]
  We propose Frequency-Aware Feature Fusion (FreqFusion) for dense image prediction tasks. FreqFusion integrates an Adaptive Low-Pass Filter (ALPF) generator, an offset generator, and an Adaptive High-Pass Filter (AHPF) generator. Comprehensive visualization and quantitative analysis demonstrate that FreqFusion effectively improves feature consistency and sharpens object boundaries.
  arXiv  Detail & Related papers  (2024-08-23T07:30:34Z)
• Graph Signal Diffusion Model for Collaborative Filtering [22.727100820178414]
  Collaborative filtering is a critical technique in recommender systems. Existing studies on diffusion model lack effective solutions for modeling implicit feedback. We propose a novel Graph Signal Diffusion Model for Collaborative Filtering (named GiffCF)
  arXiv  Detail & Related papers  (2023-11-15T07:25:14Z)
• Frequency Compensated Diffusion Model for Real-scene Dehazing [6.105813272271171]
  We consider a dehazing framework based on conditional diffusion models for improved generalization to real haze. The proposed dehazing diffusion model significantly outperforms state-of-the-art methods on real-world images.
  arXiv  Detail & Related papers  (2023-08-21T06:50:44Z)
• SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Models [18.391049303136715]
  We propose a generative framework for HSI classification with diffusion models (SpectralDiff) SpectralDiff effectively mines the distribution information of high-dimensional and highly redundant data. Experiments on three public HSI datasets demonstrate that the proposed method can achieve better performance than state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-12T16:32:34Z)
• Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
  We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling. Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
  arXiv  Detail & Related papers  (2022-09-29T11:12:27Z)
• Diffusion-GAN: Training GANs with Diffusion [135.24433011977874]
  Generative adversarial networks (GANs) are challenging to train stably. We propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate instance noise. We show that Diffusion-GAN can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.
  arXiv  Detail & Related papers  (2022-06-05T20:45:01Z)
• Stabilization of generative adversarial networks via noisy scale-space [6.574517227976925]
  Generative adversarial networks (GAN) is a framework for generating fake data based on given reals. In order to stabilize GANs, the noise enlarges the overlap of the real and fake distributions. The data smoothing may reduce the dimensionality of data but suppresses the capability of GANs to learn high-frequency information.
  arXiv  Detail & Related papers  (2021-05-01T11:32:16Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)
• Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in GANs [47.92719758687014]
  We propose a novel multi-channel wavelet-based filtering method for Generative Adversarial Networks (GANs) When embedding a wavelet deconvolution layer in the generator, the resultant GAN, called WaveletGAN, takes advantage of the wavelet deconvolution to learn a filtering with multiple channels. We conducted benchmark experiments on the Fashion-MNIST, KMNIST and SVHN datasets through an open GAN benchmark tool.
  arXiv  Detail & Related papers  (2020-05-14T03:40:11Z)

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.