paper-with-me

홈 › Papers

Graph Random Neural Features for Distance-Preserving Graph Representations

2019-09-09 · ICML 2020 1 · Daniele Zambon, Cesare Alippi, Lorenzo Livi

We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks. The embedding naturally deals with graph isomorphism and preserves the metric structure of the graph domain, in probability. In addition to being an explicit embedding method, it also allows us to efficiently and effectively approximate graph metric distances (as well as complete kernel functions); a criterion to select the embedding dimension trading off the approximation accuracy with the computational cost is also provided. GRNF can be used within traditional processing methods or as a training-free input layer of a graph neural network. The theoretical guarantees that accompany GRNF ensure that the considered graph distance is metric, hence allowing to distinguish any pair of non-isomorphic graphs.

📄 PDF Abstract BibTeX arXiv:1909.03790

Code (1)

dzambon/graph-random-neural-features 공식 구현 tf

Tasks

Graph Neural Network

Similar Papers 제목 키워드 기반

Local Distance-Preserving Node Embeddings and Their Performance on Random Graphs

2025-04-11 · My Le, Luana Ruiz, Souvik Dhara

Learning node representations is a fundamental problem in graph machine learning. While existing embedding methods effectively preserve local similarity measures, they often fail to capture global functions like graph di…

Graph Representation LearningRepresentation Learning

Geodesic Distance Between Graphs: A Spectral Metric for Assessing the Stability of Graph Neural Networks

2024-06-15 · Soumen Sikder Shuvo, Ali Aghdaei, Zhuo Feng

This paper presents a spectral framework for assessing the generalization and stability of Graph Neural Networks (GNNs) by introducing a Graph Geodesic Distance (GGD) metric. For two different graphs with the same number…

Graph Matching

Free Lunch for Privacy Preserving Distributed Graph Learning

2023-05-18 · Nimesh Agrawal, Nikita Malik, Sandeep Kumar

Learning on graphs is becoming prevalent in a wide range of applications including social networks, robotics, communication, medicine, etc. These datasets belonging to entities often contain critical private information.…

Graph LearningPrivacy Preserving

Random Projections of Sparse Adjacency Matrices

2023-09-04 · Frank Qiu

We analyze a random projection method for adjacency matrices, studying its utility in representing sparse graphs. We show that these random projections retain the functionality of their underlying adjacency matrices whil…

Graph Random Features for Scalable Gaussian Processes

2025-09-03 · Matthew Zhang, Jihao Andreas Lin, Krzysztof Choromanski, Adrian Weller 외 arxiv

We study the application of graph random features (GRFs) - a recently introduced stochastic estimator of graph node kernels - to scalable Gaussian processes on discrete input spaces. We prove that (under mild assumptions…

Bayesian InferenceGaussian Processes