Improvement research of Invariant Collaborative Filtering
Bibliographic record
Abstract
The rapid expansion of e-commerce has led to product oversaturation on online platforms. To help users find their preferred products in a more efficient and accurate way, many e-commerce platforms have introduced personalized recommendation systems. Collaborative filtering is one of the most successful techniques, while it’s improvement, Invariant Collaborative Filtering (Inv-CF), aims to address the popularity bias problem of traditional CF models by capturing unbiased preferences that remain constant despite the change in popularity distributions. However, Inv-CF model still experiences some problems such as ignoring the influence of attention, causing performance less effective when analyzing the representation of implicit feedback. This paper explores the enhancement of Inv-CF, a recommendation system model designed to mitigate the influence of popularity bias. We defined the experimental framework and evaluated the performance of the improved Inv-CF on two benchmark datasets, Yahoo! R3 and COAT. And the results demonstrate significant performance gains over the original Inv-CF, highlighting the effectiveness of the proposed enhancements. In conclusion, this paper presents improvements to the Inv-CF model's loss functions, addressing issues related to popularity bias in collaborative filtering.
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 | 0.007 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.001 |
| 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".