English
Related papers

Related papers: Directed Graph Auto-Encoders

200 papers

Graph Neural Networks (GNNs) are an effective framework for representation learning of graphs. GNNs follow a neighborhood aggregation scheme, where the representation vector of a node is computed by recursively aggregating and transforming…

Machine Learning · Computer Science 2019-02-26 Keyulu Xu , Weihua Hu , Jure Leskovec , Stefanie Jegelka

Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by applying a non-uniform score (attending) to the features. Recent…

Machine Learning · Computer Science 2023-03-02 Adrián Javaloy , Pablo Sanchez-Martin , Amit Levi , Isabel Valera

In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex…

Machine Learning · Computer Science 2019-02-27 Lu Bai , Lixin Cui , Shu Wu , Yuhang Jiao , Edwin R. Hancock

Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications. However, most existing GNNs assume the graphs exhibit strong homophily in node labels, i.e., nodes with similar labels are…

Machine Learning · Computer Science 2023-02-20 Enyan Dai , Shijie Zhou , Zhimeng Guo , Suhang Wang

Graph neural networks (GNNs) are a powerful tool to learn representations on graphs by iteratively aggregating features from node neighbourhoods. Many variant models have been proposed, but there is limited understanding on both how to…

Machine Learning · Computer Science 2019-11-14 Michael Lingzhi Li , Meng Dong , Jiawei Zhou , Alexander M. Rush

In real-world networks, predicting the weight (strength) of links is as crucial as predicting the existence of the links themselves. Previous studies have primarily used shallow graph features for link weight prediction, limiting the…

Social and Information Networks · Computer Science 2024-10-29 Jinbi Liang , Cunlai Pu , Xiangbo Shu , Yongxiang Xia , Chengyi Xia

Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computationally complex…

Machine Learning · Computer Science 2026-04-23 Angelo Zangari , Peyman Baghershahi , Sourav Medya

We propose a novel node embedding of directed graphs to statistical manifolds, which is based on a global minimization of pairwise relative entropy and graph geodesics in a non-linear way. Each node is encoded with a probability density…

Machine Learning · Computer Science 2020-02-07 Thorben Funke , Tian Guo , Alen Lancic , Nino Antulov-Fantulin

Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural network weights, and predicting generalization errors. However,…

Graph and hypergraph representation learning has attracted increasing attention from various research fields. Despite the decent performance and fruitful applications of Graph Neural Networks (GNNs), Hypergraph Neural Networks (HGNNs), and…

Machine Learning · Computer Science 2023-11-15 Minhao Zou , Zhongxue Gan , Yutong Wang , Junheng Zhang , Dongyan Sui , Chun Guan , Siyang Leng

Autoencoders based on Graph Neural Networks (GNNs) have garnered significant attention in recent years for their ability to extract informative latent representations, characterizing the structure of complex topologies, such as graphs.…

There has been a surge of recent interest in learning representations for graph-structured data. Graph representation learning methods have generally fallen into three main categories, based on the availability of labeled data. The first,…

Machine Learning · Computer Science 2022-04-13 Ines Chami , Sami Abu-El-Haija , Bryan Perozzi , Christopher Ré , Kevin Murphy

A graph neural network (GNN) is a good choice for predicting the chemical properties of molecules. Compared with other deep networks, however, the current performance of a GNN is limited owing to the "curse of depth." Inspired by…

Machine Learning · Computer Science 2020-08-19 Katsuhiko Ishiguro , Kenta Oono , Kohei Hayashi

Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous graph neural networks (GNN) require a large…

Machine Learning · Computer Science 2020-09-04 Yanqiao Zhu , Yichen Xu , Feng Yu , Shu Wu , Liang Wang

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods do not learn representations that can be interpreted in a straightforward…

Machine Learning · Computer Science 2021-01-05 Effrosyni Simou , Dorina Thanou , Pascal Frossard

Deep learning on graphs has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks, which is in contrast with advances in generative models for images and text. Is it…

Machine Learning · Computer Science 2018-02-13 Martin Simonovsky , Nikos Komodakis

Latent representations of drugs and their targets produced by contemporary graph autoencoder-based models have proved useful in predicting many types of node-pair interactions on large networks, including drug-drug, drug-target, and…

Biomolecules · Quantitative Biology 2022-11-01 Nhat Khang Ngo , Truong Son Hy , Risi Kondor

The message-passing mechanism of graph convolutional networks (i.e., GCNs) enables label information to reach more unlabeled neighbors, thereby increasing the utilization of labels. However, the additional label information does not always…

Machine Learning · Computer Science 2025-05-23 Jincheng Huang , Yujie Mo , Xiaoshuang Shi , Lei Feng , Xiaofeng Zhu

Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite…

Image and Video Processing · Electrical Eng. & Systems 2023-07-19 Diego Valsesia , Giulia Fracastoro , Enrico Magli

We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with…

Machine Learning · Computer Science 2019-05-15 Hongyang Gao , Shuiwang Ji