Recurrent Temporal Revision Graph Networks
This work addresses a bottleneck in temporal graph modeling for real-world applications like e-commerce, offering a more accurate method for neighbor aggregation.
The paper tackles the problem of incomplete and biased neighbor information in temporal graph networks by proposing a novel framework that uses recurrent neural networks with node-wise hidden states to integrate all historical neighbors, achieving a +9.6% improvement in averaged precision on an Ecommerce dataset.
Temporal graphs offer more accurate modeling of many real-world scenarios than static graphs. However, neighbor aggregation, a critical building block of graph networks, for temporal graphs, is currently straightforwardly extended from that of static graphs. It can be computationally expensive when involving all historical neighbors during such aggregation. In practice, typically only a subset of the most recent neighbors are involved. However, such subsampling leads to incomplete and biased neighbor information. To address this limitation, we propose a novel framework for temporal neighbor aggregation that uses the recurrent neural network with node-wise hidden states to integrate information from all historical neighbors for each node to acquire the complete neighbor information. We demonstrate the superior theoretical expressiveness of the proposed framework as well as its state-of-the-art performance in real-world applications. Notably, it achieves a significant +9.6% improvement on averaged precision in a real-world Ecommerce dataset over existing methods on 2-layer models.