English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graph regression is a fundamental task and has received increasing attentionin a wide range of graph learning tasks. However, the inference process isoften not interpretable. Most existing explanation techniques are limited tounderstanding GNN behaviors in classification tasks. In this work, we seek anexplanation to interpret the graph regression models (XAIG-R). We show thatexisting methods overlook the distribution shifting and continuously ordereddecision boundary, which hinders them away from being applied in the regressiontasks. To address these challenges, we propose a novel objective based on theinformation bottleneck theory and introduce a new mix-up framework, which couldsupport various GNNs in a model-agnostic manner. We further present acontrastive learning strategy to tackle the continuously ordered labels inregression task. To empirically verify the effectiveness of the proposedmethod, we introduce three benchmark datasets and a real-life dataset forevaluation. Extensive experiments show the effectiveness of the proposed methodin interpreting GNN models in regression tasks.

RegExplainer: Generating Explanations for Graph Neural Networks in Regression Task