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

Graphs are ubiquitous in many applications, such as social networks,knowledge graphs, smart grids, etc.. Graph neural networks (GNN) are thecurrent state-of-the-art for these applications, and yet remain obscure tohumans. Explaining the GNN predictions can add transparency. However, as manygraphs are not static but continuously evolving, explaining changes inpredictions between two graph snapshots is different but equally important.Prior methods only explain static predictions or generate coarse or irrelevantexplanations for dynamic predictions. We define the problem of explainingevolving GNN predictions and propose an axiomatic attribution method touniquely decompose the change in a prediction to paths on computation graphs.The attribution to many paths involving high-degree nodes is still notinterpretable, while simply selecting the top important paths can be suboptimalin approximating the change. We formulate a novel convex optimization problemto optimally select the paths that explain the prediction evolution.Theoretically, we prove that the existing method based onLayer-Relevance-Propagation (LRP) is a special case of the proposed algorithmwhen an empty graph is compared with. Empirically, on seven graph datasets,with a novel metric designed for evaluating explanations of prediction change,we demonstrate the superiority of the proposed approach over existing methods,including LRP, DeepLIFT, and other path selection methods.

Explaining GNN over Evolving Graphs using Information Flow