Node Embedding over Temporal Graphs
This work addresses the problem of learning dynamic node representations for temporal graphs, which is incremental as it builds on existing static embedding methods by adding temporal alignment and optimization.
The authors tackled node embedding in temporal graphs by developing an algorithm that learns graph evolution over time and incorporates it into embeddings for tasks like link prediction and node classification, showing performance improvements across various datasets, especially for less cohesive graphs.
In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incorporates this dynamics in a temporal node embedding framework for different graph prediction tasks. We present a joint loss function that creates a temporal embedding of a node by learning to combine its historical temporal embeddings, such that it optimizes per given task (e.g., link prediction). The algorithm is initialized using static node embeddings, which are then aligned over the representations of a node at different time points, and eventually adapted for the given task in a joint optimization. We evaluate the effectiveness of our approach over a variety of temporal graphs for the two fundamental tasks of temporal link prediction and multi-label node classification, comparing to competitive baselines and algorithmic alternatives. Our algorithm shows performance improvements across many of the datasets and baselines and is found particularly effective for graphs that are less cohesive, with a lower clustering coefficient.