Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters

• URL: http://arxiv.org/abs/2306.16976v1
• Date: Thu, 29 Jun 2023 14:31:07 GMT
• Title: Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters
• Abstract summary: High-order Graph Neural Networks (HO-GNNs) have been developed to infer consistent latent spaces in the heterophilic regime. Homophiliation, i.e., the process of learning piecewise smooth latent spaces in the heterophilic regime, is formulated as a Dirichlet problem.
• Score: 10.357474047610172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-order Graph Neural Networks (HO-GNNs) have been developed to infer consistent latent spaces in the heterophilic regime, where the label distribution is not correlated with the graph structure. However, most of the existing HO-GNNs are hop-based, i.e., they rely on the powers of the transition matrix. As a result, these architectures are not fully reactive to the classification loss and the achieved structural filters have static supports. In other words, neither the filters' supports nor their coefficients can be learned with these networks. They are confined, instead, to learn combinations of filters. To address the above concerns, we propose Diffusion-jump GNNs a method relying on asymptotic diffusion distances that operates on jumps. A diffusion-pump generates pairwise distances whose projections determine both the support and coefficients of each structural filter. These filters are called jumps because they explore a wide range of scales in order to find bonds between scattered nodes with the same label. Actually, the full process is controlled by the classification loss. Both the jumps and the diffusion distances react to classification errors (i.e. they are learnable). Homophiliation, i.e., the process of learning piecewise smooth latent spaces in the heterophilic regime, is formulated as a Dirichlet problem: the known labels determine the border nodes and the diffusion-pump ensures a minimal deviation of the semi-supervised grouping from a canonical unsupervised grouping. This triggers the update of both the diffusion distances and, consequently, the jumps in order to minimize the classification error. The Dirichlet formulation has several advantages. It leads to the definition of structural heterophily, a novel measure beyond edge heterophily. It also allows us to investigate links with (learnable) diffusion distances, absorbing random walks and stochastic diffusion.

Related papers

• Branching stochastic mechanics. I. Clustering and connected correlations within a branching-process representation of the Schrödinger equation [0.0]
  finite-range correlations in the statistics of an extended quantum state?<n>The Schrdinger-Nagasawa represents the wave function by positive forward and backward diffusion fields.<n>We show that an extended Born density and a finite correlation range can coexist in one kernel.
  arXiv  Detail & Related papers  (2026-08-30T14:19:07Z)
• Probing and steering biology across Boltz-1s trunk-diffusion boundary [32.505127447635864]
  We analyze per-residue activations from the Pairformer trunk and diffusion module of Boltz-1 using linear probes, sparse autoencoders, and causal interventions.<n>We release the trained trunk and diffusion SAEs, Boltz-1 per-residue activations, and the analysis code.
  arXiv  Detail & Related papers  (2026-08-11T22:25:42Z)
• Fluid-DiT: Graph-Free Diffusion Transformers for Fluid Flow Simulations Learning [50.053186229257555]
  We propose a Graph-Free Diffusion Transformer that replaces graph message passing with attention-based denoising.<n>By leveraging the transformer's global receptive field, Fluid-DiT naturally captures both local flow structures and long-range correlations.<n>It consistently outperforms graph-based diffusion baselines in both sample quality and distributional accuracy.
  arXiv  Detail & Related papers  (2026-08-07T12:28:45Z)
• Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion [23.795460583709907]
  We introduce Sticky Jump Diffusions (SJDs) on $mathbb Rd$ whose discrete anchors are token embeddings.<n>In forward time, anchors release their mass at a hazard rate and the released mass diffuses in the continuous ambient space.<n>Time reversal couples a score-driven SDE with a sticky jump kernel whose rate and destination are fixed by flux balance with the forward law.
  arXiv  Detail & Related papers  (2026-07-12T23:03:32Z)
• Authentic Discrete Diffusion Model [72.31371542619121]
  Authentic Discrete Diffusion (ADD) framework redefines prior pseudo-discrete approaches.<n>ADD reformulates the diffusion input by directly using float-encoded one-hot class data.<n> experiments demonstrate that ADD achieves superior performance on classification tasks compared to the baseline.
  arXiv  Detail & Related papers  (2025-10-01T15:51:10Z)
• 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)
• Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression [102.24287051757469]
  We study self-supervised covariance estimation in deep heteroscedastic regression. We derive an upper bound on the 2-Wasserstein distance between normal distributions. Experiments over a wide range of synthetic and real datasets demonstrate that the proposed 2-Wasserstein bound coupled with pseudo label annotations results in a computationally cheaper yet accurate deep heteroscedastic regression.
  arXiv  Detail & Related papers  (2025-02-14T22:37:11Z)
• The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs [59.03660013787925]
  We introduce the Heterophily Snowflake Hypothesis and provide an effective solution to guide and facilitate research on heterophilic graphs. Our observations show that our framework acts as a versatile operator for diverse tasks. It can be integrated into various GNN frameworks, boosting performance in-depth and offering an explainable approach to choosing the optimal network depth.
  arXiv  Detail & Related papers  (2024-06-18T12:16:00Z)
• What can we learn from diffusion about Anderson localization of a degenerate Fermi gas? [0.0]
  We experimentally study a degenerate, spin-polarized Fermi gas in a disorder potential formed by an optical speckle pattern. We find that some show signatures for a transition to localization above a critical disorder strength, while others show a smooth crossover to a modified diffusion regime. Our work emphasizes that the transition toward localization can be investigated by closely analyzing the system's diffusion.
  arXiv  Detail & Related papers  (2023-11-13T17:46:08Z)
• Anisotropic Diffusion Stencils: From Simple Derivations over Stability Estimates to ResNet Implementations [6.923007095578702]
  We study a large family of finite difference discretisations on a 3 x 3 stencil. We derive it by splitting 2-D anisotropic diffusion into four 1-D diffusions. We establish a bound on the spectral norm of the matrix corresponding to the stencil.
  arXiv  Detail & Related papers  (2023-09-11T16:03:00Z)
• Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems [64.29491112653905]
  We propose a novel and efficient diffusion sampling strategy that synergistically combines the diffusion sampling and Krylov subspace methods. Specifically, we prove that if tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG with the denoised data ensures the data consistency update to remain in the tangent space. Our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
  arXiv  Detail & Related papers  (2023-03-10T07:42:49Z)
• 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)
• Time-inhomogeneous diffusion geometry and topology [69.55228523791897]
  Diffusion condensation is a time-inhomogeneous process where each step first computes and then applies a diffusion operator to the data. We theoretically analyze the convergence and evolution of this process from geometric, spectral, and topological perspectives. Our work gives theoretical insights into the convergence of diffusion condensation, and shows that it provides a link between topological and geometric data analysis.
  arXiv  Detail & Related papers  (2022-03-28T16:06:17Z)
• Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs [16.88394293874848]
  We use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs. By considering a hierarchy of increasingly general sheaves, we study how the ability of the sheaf diffusion process to achieve linear separation of the classes in the infinite time limit expands. We prove that when the sheaf is non-trivial, discretised parametric diffusion processes have greater control than GNNs over their behaviour.
  arXiv  Detail & Related papers  (2022-02-09T17:25:02Z)
• Efficient recurrent neural network methods for anomalously diffusing single particle short and noisy trajectories [0.08594140167290096]
  We present a data-driven method able to infer the anomalous exponent and to identify the type of anomalous diffusion process behind single, noisy and short trajectories. A combination of convolutional and recurrent neural networks were used to achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2021-08-05T20:04:37Z)
• Interpreting diffusion score matching using normalizing flow [22.667661526643265]
  We show that diffusion score matching (DSM) (or diffusion Stein discrepancy (DSD)) is equivalent to the original score matching (or Stein discrepancy) evaluated in a normalizing flow. Specifically, we prove that DSM (or DSD) is equivalent to the original score matching (or Stein discrepancy) evaluated in the transformed space defined by the normalizing flow.
  arXiv  Detail & Related papers  (2021-07-21T13:27:32Z)
• Embedding Propagation: Smoother Manifold for Few-Shot Classification [131.81692677836202]
  We propose to use embedding propagation as an unsupervised non-parametric regularizer for manifold smoothing in few-shot classification. We empirically show that embedding propagation yields a smoother embedding manifold. We show that embedding propagation consistently improves the accuracy of the models in multiple semi-supervised learning scenarios by up to 16% points.
  arXiv  Detail & Related papers  (2020-03-09T13:51:09Z)
• Anisotropy-mediated reentrant localization [62.997667081978825]
  We consider a 2d dipolar system, $d=2$, with the generalized dipole-dipole interaction $sim r-a$, and the power $a$ controlled experimentally in trapped-ion or Rydberg-atom systems. We show that the spatially homogeneous tilt $beta$ of the dipoles giving rise to the anisotropic dipole exchange leads to the non-trivial reentrant localization beyond the locator expansion.
  arXiv  Detail & Related papers  (2020-01-31T19:00:01Z)

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.