Johannes Gasteiger, Stephan Ünnemann, Aleksandar Bojchevski
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness. Moreover, they do not account for sparsity in the input which, as our findings show, is often essential for obtaining nontrivial guarantees. We propose a model-agnostic certificate based on the randomized smoothing framework which subsumes earlier work and is tight, efficient, and sparsity-aware. Its computational complexity does not depend on the number of discrete categories or the dimension of the input (e.g. the graph size), making it highly scalable. We show the effectiveness of our approach on a wide variety of models, datasets, and tasksspecifically highlighting its use for Graph Neural Networks. So far, obtaining provable guarantees for GNNs has been difficult due to the discrete and non-i.i.d. nature of graph data. Our method can certify any GNN and handles perturbations to both the graph structure and the node attributes. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2008.12952")
get_code_for_paper("2008.12952")
have("2008.12952")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2008.12952.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2008.12952)
Connect an agent — have() is free.