Robust incomplete multi-modal clustering with interpolation enhancement and dual-path contrastive optimization
Bibliographic record
Abstract
Incomplete multi-modal clustering (IMC) has emerged as a critical challenge in the context of real-world sensing systems, where missing modalities frequently occur due to sensor failure, occlusion, or transmission loss. This paper proposes a novel dual-path clustering framework to address the limitations of existing IMC methods, which either suffer from over-reliance on reconstruction or lack adaptability to varying missing patterns. Specifically, the proposed approach dynamically selects an optimization pathway based on the global missing rate: a contrastive alignment strategy for low missing rates and a gated interpolation-enhanced module for high missing scenarios. To ensure robust representation, the model introduces residual gating to mitigate interpolation noise, and employs dual-level contrastive learning across features and soft cluster assignments to maintain semantic consistency. A self-refining pseudo-label optimization mechanism further guides the training process to convergence. Extensive experiments conducted on three public multi-modal datasets demonstrate that our method achieves competitive or superior clustering performance under various missing rates, while significantly reducing memory consumption and training time compared to state-of-the-art baselines. These findings suggest that the proposed method is well-suited for deployment in edge-intelligent systems and other resource-constrained environments.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| 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".