Database Paper Browser

Back to papers

D3-GNN: Dynamic Distributed Dataflow for Streaming Graph Neural Networks

Summary: D3-GNN: distributed hybrid-parallel streaming GNN that unrolls a distributed computation graph to maintain dynamic node embeddings online with fault-tolerance, low latency, and balanced load. Introduces inter-/intra-layer windowed forward-pass to curb skew and neighbor explosion; shows ~76× throughput vs DGL and further ~10× runtime and up to 15× message-volume reduction at high parallelism. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13497
Venue
VLDB
Year
2024
Pagerank
4.5052127e-05
Overall Rank
8,463 | 41.13%
DOI
10.14778/3681954.3681961

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 13 of 13 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers