Timezone: »

 
Cache-memory gated graph neural networks
Guixiang Ma · Vy Vo · Nesreen K. Ahmed · Theodore Willke

@
in Memory in Artificial and Real Intelligence (MemARI) »
Event URL: https://openreview.net/forum?id=EDheExoQuJN »

While graph neural networks (GNNs) provide a powerful way to learn structured representations, it remains challenging to learn long-range dependencies between graph nodes. Recurrent gated GNNs only partly address this problem. We introduce a memory augmentation to a gated GNN which simply stores the previous hidden states in a cache. We show that the cache-memory gated GNN outperforms other models on a synthetic task that requires long-range information, as well as tasks on real-world datasets.

Author Information

Guixiang Ma (Intel Labs)
Vy Vo (Intel Corporation)
Nesreen K. Ahmed (Intel Labs)
Theodore Willke (Intel Corporation)

More from the Same Authors