paper-with-me

Papers

Implicit Graph Neural Networks

2020-09-14 · NeurIPS 2020 12 · Fangda Gu, Heng Chang, Wenwu Zhu, Somayeh Sojoudi, Laurent El Ghaoui

Graph Neural Networks (GNNs) are widely used deep learning models that learn meaningful representations from graph-structured data. Due to the finite nature of the underlying recurrent structure, current GNN methods may struggle to capture long-range dependencies in underlying graphs. To overcome this difficulty, we propose a graph learning framework, called Implicit Graph Neural Networks (IGNN), where predictions are based on the solution of a fixed-point equilibrium equation involving implicitly defined "state" vectors. We use the Perron-Frobenius theory to derive sufficient conditions that ensure well-posedness of the framework. Leveraging implicit differentiation, we derive a tractable projected gradient descent method to train the framework. Experiments on a comprehensive range of tasks show that IGNNs consistently capture long-range dependencies and outperform the state-of-the-art GNN models.

📄 PDF Abstract BibTeX arXiv:2009.06211

Code (1)

SwiftieH/IGNN 공식 구현 pytorch

Tasks

Graph Learning

Similar Papers 제목 키워드 기반

How Powerful is Implicit Denoising in Graph Neural Networks

2022-09-29 · Songtao Liu, Rex Ying, Hanze Dong, Lu Lin 외

Graph Neural Networks (GNNs), which aggregate features from neighbors, are widely used for graph-structured data processing due to their powerful representation learning capabilities. It is generally believed that GNNs c…

DenoisingRepresentation Learning

Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing

2023-08-07 · Guoji Fu, Mohammed Haroon Dupty, Yanfei Dong, Lee Wee Sun

Implicit Graph Neural Networks (GNNs) have achieved significant success in addressing graph learning problems recently. However, poorly designed implicit GNN layers may have limited adaptability to learn graph metrics, e…

Generalization BoundsGraph ClassificationGraph Learning

Semi-Implicit Graph Variational Auto-Encoders

2019-08-19 · NeurIPS 2019 12 · Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Krishna R. Narayanan 외

Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable n…

DecoderVariational Inference

Graph Information Vanishing Phenomenon inImplicit Graph Neural Networks

2021-03-02 · Haifeng Li, Jun Cao, Jiawei Zhu, Qing Zhu 외

One of the key problems of GNNs is how to describe the importance of neighbor nodes in the aggregation process for learning node representations. A class of GNNs solves this problem by learning implicit weights to repres…

Graph Attention

Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting

2022-10-12 · Hongyuan Yu, Ting Li, Weichen Yu, Jianguo Li 외

Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal correlation simultaneously. However, mo…

Graph GenerationGraph structure learningMultivariate Time Series ForecastingTime Series+2