Performance Analysis of a Multicore Approach Proposed for Efficient Community Detection and Recommendation System
Bibliographic record
Abstract
Community detection is a well-known area of research that yields essential results in various fields such as social media, biological networks, pandemic spread, recommendation systems, etc. There are two important areas for improvement in existing community detection algorithms: quality of community formed should be improved and a parallel approach to community detection is needed to handle massive data. In this paper, we have proposed a three-step parallel algorithm, Par-Com, using the concept of k Clique and modularity optimization to address both of the above issues. The proposed algorithm increases the execution speed and also improves the quality of the community formed by optimizing modularity. Par-Com uses dynamic load balancing on the multicore architecture of Supercomputer ParamShivay. We have also evaluated Par-Com’s performance against nine sequential and three parallel community detection algorithms on varying size datasets, i.e. karate, macaque, email, immuno, soc-epinions, facebook, and com-Friendster. The experiment result shows that Par-Com outperforms other algorithms under consideration with up to 45% increase in modularity and up to 84% increase in execution speed. Par-Com is also capable of detecting overlapping communities, fuzzy membership of each node, most influential node in each community formed, and outlier nodes. Nodes within a community that have the highest influence are deemed as experts. The choices made by an expert in a particular community are served as recommendations to other users within that community.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".