Advances in Collaborative Filtering and Ranking

Wu, Liwei

doi:10.48550/arxiv.2002.12312

Cited by 1 publication

(2 citation statements)

References 58 publications

(148 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For Movielens-1M, we set the maximum sequence length to 200, and for the other two datasets, it is set to 50, which is approximately proportional to the average number of operations per user. The number of block B is 4 and other hyperparameters are just followed in [1].…”

Section: Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Ti-SSE: a time interval based sequential recommendation model via stochastic shared embeddings

Xiang

Lan

Wang

2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

Sequential recommendation systems attempt to use the sequence of user interactions to predict users' next behavior according to their recent based on their most recent actions. Markov chains, recurrent neural networks and self-attention have been widely developed because of their traditional ability to capture the dynamics of sequential patterns. However, most of these models make a simplified assumption that they treat the interaction history as an ordered sequence and ignore the time interval between each interaction. In other words, their model is a time series without considering the actual time interval. In this paper, we try to explicitly model the interactive timestamp in a sequence model framework and explore the impact of different time intervals on the prediction of the next project. We propose the model Ti-SSE which combines TiSASRec and SSE-PT model. Thus, we avoid the shortcomings of the traditional sequential recommendation models that ignore the absolute time intervals while the Stochastic Shared Embeddings (SSE) regularization makes our model far from overfitting due to excessive use of self-attention blocks. The results on several datasets show that our model Ti-SSE has advantages over the previous models.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

“…Therefore, researches in sequential recommendation system mainly focus on how to capture high-order dynamic information briefly. Traditionally, recommendation system works mainly focus on standard ranking approaches and collaborative filtering [1] . The sequential recommendation is a relatively new and significant problem.…”

Section: Introductionmentioning

confidence: 99%