paper-with-me

홈 › Papers

Transferability Properties of Graph Neural Networks

2021-12-09 · Luana Ruiz, Luiz F. O. Chamon, Alejandro Ribeiro

Graph neural networks (GNNs) are composed of layers consisting of graph convolutions and pointwise nonlinearities. Due to their invariance and stability properties, GNNs are provably successful at learning representations from data supported on moderate-scale graphs. However, they are difficult to learn on large-scale graphs. In this paper, we study the problem of training GNNs on graphs of moderate size and transferring them to large-scale graphs. We use graph limits called graphons to define limit objects for graph filters and GNNs -- graphon filters and graphon neural networks (WNNs) -- which we interpret as generative models for graph filters and GNNs. We then show that graphon filters and WNNs can be approximated by graph filters and GNNs sampled from them on weighted and stochastic graphs. Because the error of these approximations can be upper bounded, by a triangle inequality argument we can further bound the error of transferring a graph filter or a GNN across graphs. Our results show that (i) the transference error decreases with the graph size, and (ii) that graph filters have a transferability-discriminability tradeoff that in GNNs is alleviated by the scattering behavior of the nonlinearity. These findings are demonstrated empirically in a movie recommendation problem and in a decentralized control task.

📄 PDF Abstract BibTeX arXiv:2112.04629

Code (0)

등록된 구현이 없습니다.

Tasks

Movie Recommendation

Similar Papers 제목 키워드 기반

Stable and Transferable Hyper-Graph Neural Networks

2022-11-11 · Mikhail Hayhoe, Hans Riess, Victor M. Preciado, Alejandro Ribeiro

We introduce an architecture for processing signals supported on hypergraphs via graph neural networks (GNNs), which we call a Hyper-graph Expansion Neural Network (HENN), and provide the first bounds on the stability an…

Properties that allow or prohibit transferability of adversarial attacks among quantized networks

2024-05-15 · Abhishek Shrestha, Jürgen Großmann

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Further, these adversarial examples are found to be transferable from the source network in which they are crafted to a black-box target net…

Quantization

Limits, approximation and size transferability for GNNs on sparse graphs via graphops

2023-06-07 · NeurIPS 2023 11

Can graph neural networks generalize to graphs that are different from the graphs they were trained on, e.g., in size? In this work, we study this question from a theoretical perspective. While recent work established su…

Graph Neural Networks: Architectures, Stability and Transferability

2020-08-04 · Luana Ruiz, Fernando Gama, Alejandro Ribeiro

Graph Neural Networks (GNNs) are information processing architectures for signals supported on graphs. They are presented here as generalizations of convolutional neural networks (CNNs) in which individual layers contain…

Recommendation Systems

Graph neural networks and non-commuting operators

2024-11-06 · Mauricio Velasco, Kaiying O'Hare, Bernardo Rychtenberg, Soledad Villar

Graph neural networks (GNNs) provide state-of-the-art results in a wide variety of tasks which typically involve predicting features at the vertices of a graph. They are built from layers of graph convolutions which serv…

Inductive Bias