Incremental and effective data summarization for dynamic hierarchical clustering
Bibliographic record
Abstract
Mining informative patterns from very large, dynamically changing databases poses numerous interesting challenges. Data summarizations (e.g., data bubbles) have been proposed to compress very large static databases into representative points suitable for subsequent effective hierarchical cluster analysis. In many real world applications, however, the databases dynamically change due to frequent insertions and deletions, possibly changing the data distribution and clustering structure over time. Completely reapplying both the data summarization and the clustering algorithm to detect the changes in the clustering structure and update the uncovered data patterns following such deletions and insertions is prohibitively expensive for large fast changing databases. In this paper, we propose a new scheme to maintain data bubbles incrementally. By using incremental data bubbles, a high-quality hierarchical clustering is quickly available at any point in time. In our scheme, a quality measure for incremental data bubbles is used to identify data bubbles that do not compress well their underlying data points after certain insertions and deletions. Only these data bubbles are re-built using efficient split and merge operations. An extensive experimental evaluation shows that the incremental data bubbles provide significantly faster data summarization than completely re-building the data bubbles after a certain number of insertions and deletions, and are effective in preserving (and in some cases even improving) the quality of the data summarization.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".