TAI2Vec learns item embeddings by adapting temporal context definitions to each user's interaction pace, either via personalized session segmentation or continuous decay weighting, and shows gains over static baselines on eight datasets.
InPro- ceedings of the 46th International ACM SIGIR Conference on Research and Develop- ment in Information Retrieval(Taipei, Taiwan)(SIGIR ’23)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts
TAI2Vec learns item embeddings by adapting temporal context definitions to each user's interaction pace, either via personalized session segmentation or continuous decay weighting, and shows gains over static baselines on eight datasets.