The code is inconsistent with the one described in paper

[Yelrose]

In your paper, it's mentioned that the graph is constructed by all the session.

In https://arxiv.org/pdf/1811.00855.pdf, page 6 the first paragraph under subtitle Comparison with Variants of Connection Schemes
Firstly, we aggregate all session sequences together and model them as a directed whole item graph, which is termed as the global graph hereafter.

But in your code, both your tensorflow and pytorch version, your code comment the build_graph function and model each session sequence as one small directed graph.

[SXKDZ]

The SR-GNN models each session sequence as a directed graph. The other are model variants.