Cuckoo Heavy Keeper and the balancing act of maintaining heavy hitters in stream processing
Summary: Introduces Cuckoo Heavy Keeper (CHK), an inverted sketch distinguishing frequent vs infrequent items to unlock new throughput/memory/accuracy tradeoffs. Its parallel framework yields 1.7–5.7× throughput and up to 10^4× accuracy gains with near-linear scale-up. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 398 | Mergeable Summaries | 2012 | PODS | 0.00024383201 |
| 475 | Bottom-Up Computation of Sparse and Iceberg CUBEs | 1999 | SIGMOD | 0.00022238407 |
| 598 | Computing Iceberg Queries Efficiently | 1998 | VLDB | 0.00019431661 |
| 831 | Finding Frequent Items in Data Streams | 2008 | VLDB | 0.00016094846 |
| 1,586 | Augmented Sketch: Faster and More Accurate Stream Processing | 2016 | SIGMOD | 0.00011245213 |
| 3,491 | Holistic UDAFs at Streaming Speeds | 2004 | SIGMOD | 7.0436671e-05 |
| 5,082 | Approximate Frequency Counts over Data Streams | 2012 | VLDB | 5.7066369e-05 |
Previous
Page 1 / 1
Next