BADGNN adds a Lipschitz regularizer and an attention-temperature adjustment so that memory-based dynamic GNNs can train with large batches while keeping predictive accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams
BADGNN adds a Lipschitz regularizer and an attention-temperature adjustment so that memory-based dynamic GNNs can train with large batches while keeping predictive accuracy.