Sparse Training of Discrete Diffusion Models for Graph Generation

• URL: http://arxiv.org/abs/2311.02142v2
• Date: Wed, 22 May 2024 16:55:51 GMT
• Title: Sparse Training of Discrete Diffusion Models for Graph Generation
• Authors: Yiming Qin, Clement Vignac, Pascal Frossard,
• Abstract summary: We introduce SparseDiff, a novel diffusion model based on the observation that almost all large graphs are sparse. By selecting a subset of edges, SparseDiff effectively leverages sparse graph representations both during the noising process and within the denoising network. Our model demonstrates state-of-the-art performance across multiple metrics on both small and large datasets.
• Score: 45.103518022696996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as a cluster structure within graphs, thus limiting their applicability. To address this, we introduce SparseDiff, a novel diffusion model based on the observation that almost all large graphs are sparse. By selecting a subset of edges, SparseDiff effectively leverages sparse graph representations both during the noising process and within the denoising network, which ensures that space complexity scales linearly with the number of chosen edges. During inference, SparseDiff progressively fills the adjacency matrix with the selected subsets of edges, mirroring the training process. Our model demonstrates state-of-the-art performance across multiple metrics on both small and large datasets, confirming its effectiveness and robustness across varying graph sizes. It also ensures faster convergence, particularly on larger graphs, achieving a fourfold speedup on the large Ego dataset compared to dense models, thereby paving the way for broader applications.

Related papers

• Input Snapshots Fusion for Scalable Discrete Dynamic Graph Nerual Networks [27.616083395612595]
  We introduce an Input bf Snapshots bf Fusion based bf Dynamic bf Graph Neural Network (SFDyG) By eliminating the partitioning of snapshots within the input window, we obtain a multi-graph (more than one edge between two nodes) We propose a scalable three-step mini-batch training method and demonstrate its equivalence to full-batch training counterpart.
  arXiv  Detail & Related papers  (2024-05-11T10:05:55Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
  We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
  arXiv  Detail & Related papers  (2022-12-01T11:49:07Z)
• NVDiff: Graph Generation through the Diffusion of Node Vectors [20.424372965054832]
  We propose NVDiff, which takes the VGAE structure and uses a score-based generative model (SGM) as a flexible prior to sample node vectors. Built on the NVDiff framework, we introduce an attention-based score network capable of capturing both local and global contexts of graphs.
  arXiv  Detail & Related papers  (2022-11-19T20:43:39Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• Effective and Efficient Graph Learning for Multi-view Clustering [173.8313827799077]
  We propose an effective and efficient graph learning model for multi-view clustering. Our method exploits the view-similar between graphs of different views by the minimization of tensor Schatten p-norm. Our proposed algorithm is time-economical and obtains the stable results and scales well with the data size.
  arXiv  Detail & Related papers  (2021-08-15T13:14:28Z)
• T-LoHo: A Bayesian Regularization Model for Structured Sparsity and Smoothness on Graphs [0.0]
  In graph-structured data, structured sparsity and smoothness tend to cluster together. We propose a new prior for high dimensional parameters with graphical relations. We use it to detect structured sparsity and smoothness simultaneously.
  arXiv  Detail & Related papers  (2021-07-06T10:10:03Z)
• Scaling Graph Clustering with Distributed Sketches [1.1011268090482575]
  We present a method inspired by spectral clustering where we instead use matrix sketches derived from random dimension-reducing projections. We show that our method produces embeddings that yield performant clustering results given a fully-dynamic block model stream. We also discuss the effects of block model parameters upon the required dimensionality of the subsequent embeddings, and show how random projections could significantly improve the performance of graph clustering in distributed memory.
  arXiv  Detail & Related papers  (2020-07-24T17:38:04Z)
• Block-Approximated Exponential Random Graphs [77.4792558024487]
  An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions. Our methods are scalable to sparse graphs consisting of millions of nodes.
  arXiv  Detail & Related papers  (2020-02-14T11:42:16Z)

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.