Leveraging Graph Diffusion Models for Network Refinement Tasks
- URL: http://arxiv.org/abs/2311.17856v1
- Date: Wed, 29 Nov 2023 18:02:29 GMT
- Title: Leveraging Graph Diffusion Models for Network Refinement Tasks
- Authors: Puja Trivedi, Ryan Rossi, David Arbour, Tong Yu, Franck Dernoncourt,
Sungchul Kim, Nedim Lipka, Namyong Park, Nesreen K. Ahmed, Danai Koutra
- Abstract summary: We propose a novel graph generative framework, SGDM, based on subgraph diffusion.
Our framework not only improves the scalability and fidelity of graph diffusion models, but also leverages the reverse process to perform novel, conditional generation tasks.
- Score: 72.54590628084178
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Most real-world networks are noisy and incomplete samples from an unknown
target distribution. Refining them by correcting corruptions or inferring
unobserved regions typically improves downstream performance. Inspired by the
impressive generative capabilities that have been used to correct corruptions
in images, and the similarities between "in-painting" and filling in missing
nodes and edges conditioned on the observed graph, we propose a novel graph
generative framework, SGDM, which is based on subgraph diffusion. Our framework
not only improves the scalability and fidelity of graph diffusion models, but
also leverages the reverse process to perform novel, conditional generation
tasks. In particular, through extensive empirical analysis and a set of novel
metrics, we demonstrate that our proposed model effectively supports the
following refinement tasks for partially observable networks: T1: denoising
extraneous subgraphs, T2: expanding existing subgraphs and T3: performing
"style" transfer by regenerating a particular subgraph to match the
characteristics of a different node or subgraph.
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) - Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding [51.75091298017941]
This paper proposes a novel Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) for attributed graph data.
The proposed method surpasses state-of-the-art baseline algorithms by a significant margin on different downstream tasks across popular datasets.
arXiv Detail & Related papers (2024-01-12T17:57:07Z) - A Dynamic Graph CNN with Cross-Representation Distillation for
Event-Based Recognition [21.225945234873745]
We present a new event-based graph learning framework called graph cross-representation distillation (CRD)
CRD provides additional supervision and prior knowledge for the event graph.
Our model and learning framework are effective and generalize well across multiple vision tasks.
arXiv Detail & Related papers (2023-02-08T16:35:39Z) - 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) - DiGress: Discrete Denoising diffusion for graph generation [79.13904438217592]
DiGress is a discrete denoising diffusion model for generating graphs with categorical node and edge attributes.
It achieves state-of-the-art performance on molecular and non-molecular datasets, with up to 3x validity improvement.
It is also the first model to scale to the large GuacaMol dataset containing 1.3M drug-like molecules.
arXiv Detail & Related papers (2022-09-29T12:55:03Z) - Digraphwave: Scalable Extraction of Structural Node Embeddings via
Diffusion on Directed Graphs [20.432261314154804]
Digraphwave is a scalable algorithm for extracting structural node embeddings on directed graphs.
The two embedding enhancements, named transposition and aggregation, are shown to lead to a significant increase in macro F1 score for classifying automorphic identities.
arXiv Detail & Related papers (2022-07-20T19:03:35Z) - Investigating Neighborhood Modeling and Asymmetry Preservation in
Digraph Representation Learning [12.406793386672208]
Digraph Hyperbolic Network (D-HYPR) learns node representations in hyperbolic space to avoid structural and semantic distortion of real-world digraphs.
Our code and data will be available.
arXiv Detail & Related papers (2021-12-22T08:50:55Z) - A Robust and Generalized Framework for Adversarial Graph Embedding [73.37228022428663]
We propose a robust framework for adversarial graph embedding, named AGE.
AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution.
Based on this framework, we propose three models to handle three types of graph data.
arXiv Detail & Related papers (2021-05-22T07:05:48Z) - Promoting Graph Awareness in Linearized Graph-to-Text Generation [72.83863719868364]
We study the ability of linearized models to encode local graph structures.
Our findings motivate solutions to enrich the quality of models' implicit graph encodings.
We find that these denoising scaffolds lead to substantial improvements in downstream generation in low-resource settings.
arXiv Detail & Related papers (2020-12-31T18:17:57Z)
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.