Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs (Supplementary Material)

As mentioned in Section 4 of main paper, the intricate relational and temporal dependencies between data points in our setting limits our ability to efficiently train by decomposing events into independent sequences. To address this challenge, we design an efficient Global BPTT algorithm presented below. During each step of training, we build computational graph using consecutive events in the sliding window of a fixed size. We then move sliding window further and train till the end of timeline in similar fashion which allows to capture dependencies across batches while retaining efficiency.