Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs

DGL is platform-agnostic so that it can easily be integrated with tensor-oriented frameworks like PyTorch and MXNet. It is an open-source project under active development. Appendix A summarizes the models released in DGL repository. In this paper, we compare DGL against the state-of- the-art library on multiple standard GNN setups and show the improvement of training speed and memory efficiency. 2 F RAMEWORK REQUIREMENTS OF D EEP L EARNING ON G RAPHS Message passing paradigm. Formally, we define a graph G(V,E). V is the set of nodes with v i being the feature vector associated with each node. E is the set of the edge tuples (e k,r k,s k), where s k r k represents the edge from node s k to r k, and e k is feature vector associated with the edge. DGNs are defined by the following edgewise and node-wise computation: Edgewise: m (t) k φ e (e ( t 1) k, v ( t 1) r k, v ( t 1) s k), Node-wise: v ( t) i φ v (v (t 1) i, null k s.t.