Summary of Inferring Properties Of Graph Neural Networks, by Dat Nguyen (1) et al.
Inferring Properties of Graph Neural Networks
by Dat Nguyen, Hieu M. Vu, Cong-Thanh Le, Bach Le, David Lo, ThanhVu Nguyen, Corina Pasareanu
First submitted to arxiv on: 8 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Programming Languages (cs.PL); Software Engineering (cs.SE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed GNNInfer technique is an automatic property inference method for Graph Neural Networks (GNNs). It addresses the challenge of varying input structures in GNNs by identifying influential structures and converting them to equivalent Feedforward Neural Networks (FNNs). Existing property inference techniques are then used to capture properties specific to these structures. The captured properties are generalized to any input graphs containing the influential structures, and a model is learned to estimate deviations from inferred properties. This improves property correctness and allows for extension of inferred properties with constraints. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GNNInfer is a new way to understand how Graph Neural Networks work. It helps us figure out what properties these networks have just by looking at some examples. The technique works by finding important parts of the input data that affect the network’s output, and then using this information to make predictions about other inputs. GNNInfer can even learn from its mistakes and improve over time. |
Keywords
* Artificial intelligence * Inference
