2018 · 369 citations · 21 references
ComputingComputer ScienceHuman BehaviorMachine LearningRecommender SystemsAttention NetworksRecommendation SystemsSequential RecommendationAttentionAttention-based Sequential RecommendationLong-term Preference ModelingSequential User Behavior ModelingUser Activity PatternsUser Activity RecognitionUser PreferencesUser Representation Learning
Large volumes of user activity data make it essential to model sequential behavior for recommendations, yet current methods often ignore evolving long‑term preferences and rely on linear interaction modeling. This study proposes a two‑layer hierarchical attention network to predict the next item a user may be interested in. The model first learns long‑term preferences from historical purchase representations, then fuses them with short‑term preferences in a second attention layer to generate a final user representation. Experiments show the proposed method outperforms state‑of‑the‑art baselines.
With a large amount of user activity data accumulated, it is crucial to exploit user sequential behavior for sequential recommendations. Conventionally, user general taste and recent demand are combined to promote recommendation performances. However, existing methods often neglect that user long-term preference keep evolving over time, and building a static representation for user general taste may not adequately reflect the dynamic characters. Moreover, they integrate user-item or item-item interactions through a linear way which limits the capability of model. To this end, in this paper, we propose a novel two-layer hierarchical attention network, which takes the above properties into account, to recommend the next item user might be interested. Specifically, the first attention layer learns user long-term preferences based on the historical purchased item representation, while the second one outputs final user representation through coupling user long-term and short-term preferences. The experimental study demonstrates the superiority of our method compared with other state-of-the-art ones.
21
Hierarchical Attention Networks for Document Classification
Zichao Yang, Diyi Yang, Chris Dyer et al. · 2016 · 4.8K citations · Full text
BPR: Bayesian Personalized Ranking from Implicit Feedback
Steffen Rendle, Christoph Freudenthaler, Zeno Gantner et al. · arXiv (Cornell University) · 2012 · 4.4K citations · Full text
Wide & Deep Learning for Recommender Systems
Heng-Tze Cheng, Levent Koç, Jeremiah Harmsen et al. · 2016 · 3.3K citations · Full text
Eunjoon Cho, Seth A. Myers, Jure Leskovec · 2011 · 2.9K citations