Interest-Aware Message Passing Recommender Model based on Graph Convolutional Networks
Bibliographic record
Abstract
Abstract With the rapid development of deep learning, recommender systems have become an important tool to solve the problem of information overload. Collaborative filtering-based models have made effective progress in learning user and item representations. Graph Convolutional Networks (GCN) have been introduced to extract connection characteristics between users and items, but suffer from over-smoothing issues. This paper proposes an interest-aware message passing recommendation model that uses attention mechanisms and two methods of partitioning graphs to mitigate the over-smoothing problem. The model uses two methods to partition the graph into subgraphs, namely, partitioning the users and items into subgraphs separately. High-order graph convolution operations are performed in the subgraphs to learn user-item node representations based on weak user-item relationships between subgraphs, as well as user-item node representations based on weak item-item relationships between subgraphs, in order to better express users' interests and preferences. By using attention mechanisms, attention weights are added to each layer of the graph neural network to improve the representation of more important layers in the user feature representation.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".