TY - JOUR
T1 - Not All Memories Created Equal
T2 - Dynamic User Representations for Collaborative Filtering
AU - Gaiger, Keren
AU - Barkan, Oren
AU - Tsipory-Samuel, Shir
AU - Koenigstein, Noam
N1 - Publisher Copyright:
Author
PY - 2023
Y1 - 2023
N2 - Collaborative filtering methods for recommender systems tend to represent users as a single static latent vector. However, user behavior and interests may dynamically change in the context of the recommended item being presented to the user. For example, in the case of movie recommendations, it is usually true that movies that the user watched more recently are more informative than movies that were watched a long time ago. However, it is possible that a particular movie from the past may become suddenly more relevant for prediction in the presence of a recommendation for its sequel movie. In response to this issue, we introduce the Attentive Item2Vec++ (AI2V++) model, a neural attentive collaborative filtering approach in which the user representation adapts dynamically in the presence of the recommended item. AI2V++ employs a novel context-target attention mechanism in order to learn and capture different characteristics of the user's historical behavior with respect to a potential recommended item. Furthermore, analysis of the neural-attentive scores allows for improved interpretability and explainability of the model. We evaluate our proposed approach on five publicly available datasets and demonstrate its superior performance in comparison to state-of-the-art baselines across multiple accuracy metrics.
AB - Collaborative filtering methods for recommender systems tend to represent users as a single static latent vector. However, user behavior and interests may dynamically change in the context of the recommended item being presented to the user. For example, in the case of movie recommendations, it is usually true that movies that the user watched more recently are more informative than movies that were watched a long time ago. However, it is possible that a particular movie from the past may become suddenly more relevant for prediction in the presence of a recommendation for its sequel movie. In response to this issue, we introduce the Attentive Item2Vec++ (AI2V++) model, a neural attentive collaborative filtering approach in which the user representation adapts dynamically in the presence of the recommended item. AI2V++ employs a novel context-target attention mechanism in order to learn and capture different characteristics of the user's historical behavior with respect to a potential recommended item. Furthermore, analysis of the neural-attentive scores allows for improved interpretability and explainability of the model. We evaluate our proposed approach on five publicly available datasets and demonstrate its superior performance in comparison to state-of-the-art baselines across multiple accuracy metrics.
KW - Artificial neural networks
KW - collaborative filtering
KW - neural attention
KW - recommender systems
UR - http://www.scopus.com/inward/record.url?scp=85153340677&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2023.3263931
DO - 10.1109/ACCESS.2023.3263931
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85153340677
SN - 2169-3536
VL - 11
SP - 34746
EP - 34763
JO - IEEE Access
JF - IEEE Access
ER -