ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictions
This addresses the problem of interpretability in network analysis for researchers and practitioners using NE-based LP methods, but it is incremental as it builds on existing NE techniques.
The paper tackles the lack of transparency in Network Embedding (NE) methods for Link Prediction (LP) by introducing ExplaiNE, an approach that provides counterfactual explanations by identifying existing links to explain predicted links, with empirical evaluation showing its accuracy and scalability for the Conditional Network Embedding method.
Networks are powerful data structures, but are challenging to work with for conventional machine learning methods. Network Embedding (NE) methods attempt to resolve this by learning vector representations for the nodes, for subsequent use in downstream machine learning tasks. Link Prediction (LP) is one such downstream machine learning task that is an important use case and popular benchmark for NE methods. Unfortunately, while NE methods perform exceedingly well at this task, they are lacking in transparency as compared to simpler LP approaches. We introduce ExplaiNE, an approach to offer counterfactual explanations for NE-based LP methods, by identifying existing links in the network that explain the predicted links. ExplaiNE is applicable to a broad class of NE algorithms. An extensive empirical evaluation for the NE method `Conditional Network Embedding' in particular demonstrates its accuracy and scalability.