Efficient Temporal Structural Graph Representation Learning
Presented by Janet Layne
Computing PhD Student, Computer Science emphasis
January 25, 2024 at 10:30-11:30 a.m.
City Center Plaza room 259 or register for Zoom attendance
Abstract
Node representation learning (NRL) generates numerical vectors (embeddings) for the nodes of a graph. Structural NRL specifically assigns similar node embeddings for those nodes that exhibit similar structural roles. This is in contrast with its proximity-based counterpart, wherein similarity between embeddings reflects spatial proximity among nodes. Structural NRL is useful for tasks such as node classification where nodes of the same class share structural roles, though there may exist a distant, or no path between them. Although structural NRL has been well-studied in static graphs, it has received limited attention in the temporal setting. Here, the embeddings are required to represent the evolution of nodes’ structural roles over time. The existing methods are limited in terms of efficiency and effectiveness: they scale poorly to even moderate number of timestamps, or capture structural role only tangentially. In this work, we present a novel unsupervised approach to structural representation learning for temporal graphs that overcomes these limitations. For each node, our approach clusters then aggregates the embedding of a node’s neighbors for each timestamp, followed by a further temporal aggregation of all timestamps. This is repeated for (at most) d iterations, so as to acquire information from the d-hop neighborhood of a node. Our approach takes linear time in the number of overall temporal edges, and possesses important theoretical properties that formally demonstrate its effectiveness. Extensive experiments on synthetic and real datasets show superior performance in node classification, where it is necessary to capture changes in a node’s neighborhood structure over time to identify its class. Similar results are achieved in regression experiments. We also demonstrate the superior scalability of our approach to large graphs.