A graph neural network-based reinforcement learning controller for source emission rate improves throughput by up to 13.5% and latency by up to 30% across three simulated stream topologies.
Efficient operator placement for distributed data stream processing applications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.NI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Generalised Rate Control Approach For Stream Processing Applications
A graph neural network-based reinforcement learning controller for source emission rate improves throughput by up to 13.5% and latency by up to 30% across three simulated stream topologies.