Graph Neural Network Session Recommendation Algorithm Based on Semantic Knowledge and Temporal Encoding
Bibliographic record
Abstract
Session-based recommendation aims to match users with corresponding resources, and has been widely used in streaming media, e-commerce and so on. At present, the most widely used session-based graph neural network recommendation model is to construct a session sequence into a session graph as the input of the graph neural network, and use the target attention network to capture the specific user interests associated with the target item, and use the self-attention mechanism to obtain the long-term interest preferences of the user. Although this model has achieved good results, it also has some limitations. (1) It only constructs the session sequence into a session graph, resulting in a single form of constructing the session graph. (2) It is too one-sided to recommend users only according to their session behavior. In order to solve the above problems, this paper proposes a new recommendation algorithm -Graph Neural Network Recommendation Algorithm (KT-GNN) based on semantic knowledge and temporal encoding. First, we introduce dwell time to the session graph and encode the dwell time to solve the session graph single problem. At the same time, the dwell time can reflect the user’s preference for the item and improve the efficiency of recommendation. Second, PairRE knowledge translation model is used to process users’ semantic knowledge and mine users’ semantic preferences. Extensive experiments have demonstrated the superiority of our model on both Yoochoose and TFCD datasets.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".