Spectral Embedding Representation Based on Random Anchor Graph Aggregation
Bibliographic record
Abstract
Anchor-based strategies have been widely used to accelerate spectral clustering, yet their effectiveness is directly affected by the quality of the selected anchors. Random sampling has become one of the most important anchor determination methods due to its efficiency. However, the anchors obtained by a single random sampling often fail to adequately capture the topological structure of the original data, making it difficult for the constructed anchor graph to achieve satisfactory clustering performance. To solve this problem, we propose a novel spectral embedding representation model based on random anchor graph aggregation (RAGA), in which an aggregated anchor graph can be produced to obtain enhanced sample representation capability. Specifically, we perform multiple random samplings to make the distribution of the selected anchors approximate the original data within a reasonable sampling time. Subsequently, adaptive weighted learning is performed on the contribution of the constructed multiple anchor graphs, and then an aggregated anchor graph can be formed, which can portray the topological structure of the original samples more precisely. In addition, spectral embedding and spectral rotation are integrated into a joint learning framework to reduce the model learning error accumulation caused by the traditional two-stage framework. Notably, we propose a rigorous theorem for analyzing the approximation of samples by the selected anchors in multiple random samplings. Our proposed RAGA maintains the speed advantage of random sampling while obtaining a high-quality aggregated anchor graph, enabling it to handle large-scale data scenarios. Experimental results on several benchmark datasets show that the RAGA model outperforms other state-of-the-art (SOTA) anchor graph-based clustering methods.
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 | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".