-
graphtransformer
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
I just finished reading "Benchmarking Graph Neural Networks" (Dwivedi et al. 2020) and "A Generalization of Transformer Networks to Graphs" (also Dwivedi et al. 2020), and came across the claim that Laplacian eigenvectors of a graph "represent a natural generalization of the Transformer (Vaswani et al., 2017) positional encodings (PE)". Xavier Bresson tweeted the same thing.
Code for https://arxiv.org/abs/2003.00982 found: https://github.com/graphdeeplearning/benchmarking-gnns