FDGC: Fuzzy deep clustering with dual-granularity contrastive learning
Bibliographic record
Abstract
Deep clustering has garnered considerable attention in data mining and computer vision due to its effectiveness in handling high-dimensional data. However, traditional deep clustering methods face notable limitations. Real-world data often exhibit complex feature distributions and ambiguous boundaries. Fixed network architectures struggle to capture both global and local dependencies among data samples and are inadequate for managing fuzzy boundaries. Additionally, contrastive learning methods commonly used in deep clustering suffer from inefficient negative sample selection, where many positive samples are mistakenly treated as negative, thereby hindering training. To address these challenges, this paper proposes a fuzzy deep clustering method with dual-granularity contrastive learning (FDGC). The method extracts features and clusters them to generate pseudo-labels, retaining only the reliable ones through a confidence screening mechanism for use as supervision signals. By integrating data augmentation strategies with a self-attention fuzzy network, FDGC effectively captures both context and local details while dynamically adapting to feature fuzziness. Furthermore, a dual-granularity contrastive loss function is introduced to enhance feature representation. This loss improves sample discriminability at both the cluster and instance levels, significantly mitigating the issue of inaccurate negative sampling in traditional contrastive learning. Experimental results across multiple benchmark datasets demonstrate that FDGC outperforms existing method, validating the effectiveness of the proposed approach.
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 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 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".