Diffusion Probabilistic Models for Structured Node Classification

2023-02-21 · NeurIPS 2023 11 · Hyosoon Jang, Seonghyun Park, Sangwoo Mo, Sungsoo Ahn

This paper studies structured node classification on graphs, where the predictions should consider dependencies between the node labels. In particular, we focus on solving the problem for partially labeled graphs where it is essential to incorporate the information in the known label for predicting the unknown labels. To address this issue, we propose a novel framework leveraging the diffusion probabilistic model for structured node classification (DPM-SNC). At the heart of our framework is the extraordinary capability of DPM-SNC to (a) learn a joint distribution over the labels with an expressive reverse diffusion process and (b) make predictions conditioned on the known labels utilizing manifold-constrained sampling. Since the DPMs lack training algorithms for partially labeled data, we design a novel training algorithm to apply DPMs, maximizing a new variational lower bound. We also theoretically analyze how DPMs benefit node classification by enhancing the expressive power of GNNs based on proposing AGG-WL, which is strictly more powerful than the classic 1-WL test. We extensively verify the superiority of our DPM-SNC in diverse scenarios, which include not only the transductive setting on partially labeled graphs but also the inductive setting and unlabeled graphs.

📄 PDF Abstract BibTeX arXiv:2302.10506

Code (0)

등록된 구현이 없습니다.

Tasks

Classification Node Classification

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Diffusion-Convolutional Neural Networks

2015-11-06 · NeurIPS 2016 12 · James Atwood, Don Towsley

We present diffusion-convolutional neural networks (DCNNs), a new model for graph-structured data. Through the introduction of a diffusion-convolution operation, we show how diffusion-based representations can be learned…

Classification General Classification GPU Node Classification

ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions

2025-07-19 · Yule Li, Yifeng Lu, Zhen Wang, Zhewei Wei 외 arxiv

In recent years, graph neural networks (GNN) have achieved unprecedented successes in node classification tasks. Although GNNs inherently encode specific inductive biases (e.g., acting as low-pass or high-pass filters), …

Node Classification

Diffusion Mechanism in Residual Neural Network: Theory and Applications

2021-05-07 · Tangjun Wang, Zehao Dou, Chenglong Bao, Zuoqiang Shi

Diffusion, a fundamental internal mechanism emerging in many physical processes, describes the interaction among different objects. In many learning tasks with limited training samples, the diffusion connects the labeled…

Binary Classification Classification Few-Shot Image Classification Few-Shot Learning+4

Confidence Sets for the Source of a Diffusion in Regular Trees

2015-10-19 · Justin Khim, Po-Ling Loh

We study the problem of identifying the source of a diffusion spreading over a regular tree. When the degree of each node is at least three, we show that it is possible to construct confidence sets for the diffusion sour…

Automated Construction of Sparse Bayesian Networks from Unstructured Probabilistic Models and Domain Information

2013-03-27 · Sampath Srinivas, Stuart Russell, Alice M. Agogino

An algorithm for automated construction of a sparse Bayesian network given an unstructured probabilistic model and causal domain information from an expert has been developed and implemented. The goal is to obtain a netw…