Papers of the day   All papers

INTERPRETING GRAPH NEURAL NETWORKS FOR NLP WITH DIFFERENTIABLE EDGE MASKING

Comments

Nicola De Cao: New hot pre-print 🔥Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking🔥 https://arxiv.org/abs/2010.00577 We show you can learn to remove most of the edges in GNNs such that the remaning ones are interpretable! with @michael_sejr @iatitov https://t.co/0xl3U8bxiB

4 replies, 228 likes


Thomas Kipf: GraphMask looks like a very elegant approach to generate post-hoc explanations for Graph Neural Networks

0 replies, 175 likes


Michael Schlichtkrull: Very happy to share our new preprint on interpretability for graph neural networks https://arxiv.org/abs/2010.00577!🚀 Differentiable masking reveals which edges a GNN uses, and which can be discarded. With @nicola_decao @iatitov https://t.co/oWRRwMkccL

0 replies, 142 likes


Nicola De Cao: Check out our new exiting work on interpretability for Graph Neural Networks! 🔥

0 replies, 8 likes


Michael Schlichtkrull: Check out our new work on interpretability for graph neural networks!

0 replies, 6 likes


arXiv CS-CL: Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking http://arxiv.org/abs/2010.00577

0 replies, 5 likes


arXiv CS-CL: Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking http://arxiv.org/abs/2010.00577

0 replies, 3 likes


La Forge AI: [2010.00577] Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking #NLProc https://arxiv.org/abs/2010.00577

0 replies, 1 likes


Content

Found on Oct 02 2020 at https://arxiv.org/pdf/2010.00577.pdf

PDF content of a computer science paper: INTERPRETING GRAPH NEURAL NETWORKS FOR NLP WITH DIFFERENTIABLE EDGE MASKING