2604.00555 Mini-Batch Graph Sampling with Historical Embeddings: Scaling GNNs to Billion-Edge Graphs
Graph neural networks (GNNs) demonstrate remarkable performance on node classification tasks but suffer from poor scalability: sampling large neighborhoods results in exponential neighborhood explosion, while full-batch training requires entire graphs in GPU memory. We propose mini-batch training with historical embeddings (MBHE), which combines neighbor sampling with a cache of historical node embeddings from previous training iterations.