Search Results for author:
Found 3 papers, 2 papers with code
XAI for Transformers: Better Explanations through Conservative Propagation
Transformers have become an important workhorse of machine learning, with numerous applications.
Higher-Order Explanations of Graph Neural Networks via Relevant Walks
In this paper, we show that GNNs can in fact be naturally explained using higher-order expansions, i. e. by identifying groups of edges that jointly contribute to the prediction.
Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly Detection on Text
There exist few text-specific methods for unsupervised anomaly detection, and for those that do exist, none utilize pre-trained models for distributed vector representations of words.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
