Pith. sign in

REVIEW

Reimagining GNN Explanations with ideas from Tabular Data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.12665 v1 pith:WEDAQKR3 submitted 2021-06-23 cs.LG cs.AI

Reimagining GNN Explanations with ideas from Tabular Data

classification cs.LG cs.AI
keywords dataexplanationstabulardecisionexplainabilityneuralaspectsavailable
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Explainability techniques for Graph Neural Networks still have a long way to go compared to explanations available for both neural and decision decision tree-based models trained on tabular data. Using a task that straddles both graphs and tabular data, namely Entity Matching, we comment on key aspects of explainability that are missing in GNN model explanations.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.