paper-with-me

Papers

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 specific learning tasks. The core operation in GNNs is message propagation in which each node updates its representation by aggregating its neighbors' representations. Existing GNNs mainly adopt either linear neighborhood aggregation (mean,sum) or max aggregator in their message propagation. (1) For linear aggregators, the whole nonlinearity and network's capacity of GNNs are generally limited due to deeper GNNs usually suffer from over-smoothing issue. (2) For max aggregator, it usually fails to be aware of the detailed information of node representations within neighborhood. To overcome these issues, we re-think the message propagation mechanism in GNNs and aim to develop the general nonlinear aggregators for neighborhood information aggregation in GNNs. One main aspect of our proposed nonlinear aggregators is that they provide the optimally balanced aggregators between max and mean/sum aggregations. Thus, our aggregators can inherit both (i) high nonlinearity that increases network's capacity and (ii) detail-sensitivity that preserves the detailed information of representations together in GNNs' message propagation. Promising experiments on several datasets show the effectiveness of the proposed nonlinear aggregators.

📄 PDF Abstract BibTeX arXiv:2202.09145

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passing

2025-07-27 · Xuanting Xie, Bingheng Li, Erlin Pan, Zhao Kang 외 arxiv

Graph Neural Networks (GNNs) have become a dominant approach to learning graph representations, primarily because of their message-passing mechanisms. However, GNNs typically adopt a fixed aggregator function such as Mea…

Graph Learning

Principal Neighbourhood Aggregation for Graph Nets

2020-04-12 · NeurIPS 2020 12 · Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò 외

Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on isomorphism tasks and countable feature sp…

Graph ClassificationGraph RegressionMolecular Property PredictionNode Classification

Logical Characterizations of GNNs with Mean Aggregation

2025-07-24 · Moritz Schönherr, Carsten Lutz arxiv

We study the expressive power of graph neural networks (GNNs) with mean as the aggregation function, with the following results. In the non-uniform setting, such GNNs have exactly the same expressive power as ratio modal…

Towards Powerful Graph Neural Networks: Diversity Matters

2021-01-01 · Xu Bingbing, HuaWei Shen, Qi Cao, YuanHao Liu 외

Graph neural networks (GNNs) offer us an effective framework for graph representation learning via layer-wise neighborhood aggregation. Their success is attributed to their expressive power at learning representation of …

DiversityGraph Representation LearningNode ClassificationRepresentation Learning

Learning to Pool in Graph Neural Networks for Extrapolation

2021-06-11 · Jihoon Ko, Taehyung Kwon, Kijung Shin, Juho Lee

Graph neural networks (GNNs) are one of the most popular approaches to using deep learning on graph-structured data, and they have shown state-of-the-art performances on a variety of tasks. However, according to a recent…