Multi-Mask Aggregators for Graph Neural Networks

2022-11-24 · Learning on Graphs Conference 2022 11 · Ahmet Sarıgün, Ahmet Sureyya Rifaioglu

One of the most critical operations in graph neural networks (GNNs) is the aggregation operation, which aims to extract information from neighbors of the target node. Several convolution methods have been proposed such as standard graph convolution (GCN), graph attention (GAT), and message passing (MPNN). In this study, we propose an aggregation method called Multi-Mask Aggregators (MMA), where the model learns a weighted mask for each aggregator before collecting neighboring messages. MMA draws similarities with the GAT and MPNN but has some theoretical and practical advantages. Intuitively, our framework is not limited by the number of heads from GAT and has more discriminative than an MPNN. The performance of MMA was compared with the well-known baseline methods in both node classification and graph regression tasks on widely-used benchmarking datasets, and it has shown improved performance. Dataset and codes are available at https://github.com/asarigun/mma.

📄 PDF Abstract BibTeX

Code (1)

asarigun/mma 공식 구현 pytorch

Tasks

Benchmarking Graph Regression Node Classification

Methods 이 논문이 사용한 방법론

GAT A Graph Attention Network (GAT) is a neural network architecture that operates on graph-structured data, leveraging masked self-attentional layers to address the shortcomings…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

MPNN There are at least eight notable examples of models from the literature that can be described using the Message Passing Neural Networks (MPNN) framework. For simplicity we…

Generalizing Aggregation Functions in GNNs:High-Capacity GNNs via Nonlinear Neighborhood Aggregators

2022-02-18 · Beibei Wang, Bo Jiang

Graph neural networks (GNNs) have achieved great success in many graph learning tasks. The main aspect powering existing GNNs is the multi-layer network architecture to learn the nonlinear graph representations for the s…

Graph Learning

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

2026-05-13 · Haaris Mehmood, Giorgos Tatsis, Dimitrios Alexopoulos, Karthikeyan Saravanan 외 arxiv

Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secure-aggregation schemes protect privacy against an honest-but-curious se…

Federated Learning

Breaking the Expressive Bottlenecks of Graph Neural Networks

2020-12-14 · Mingqi Yang, Yanming Shen, Heng Qi, BaoCai Yin

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs were at most as powerful as 1-WL test in …

Graph Property Prediction

Learnable Commutative Monoids for Graph Neural Networks

2022-12-16 · Euan Ong, Petar Veličković

Graph neural networks (GNNs) have been shown to be highly sensitive to the choice of aggregation function. While summing over a node's neighbours can approximate any permutation-invariant function over discrete inputs, C…

Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks

2021-09-27 · ICCV 2021 10 · Yongcheng Jing, Yiding Yang, Xinchao Wang, Mingli Song 외

In this paper, we study a novel meta aggregation scheme towards binarizing graph neural networks (GNNs). We begin by developing a vanilla 1-bit GNN framework that binarizes both the GNN parameters and the graph features.…