Multi-Resolution Attention for Personalized Item Search

Personalized item search has become an essential tool for online platforms---where users interact with a large corpus of items (e.g., click, purchase, like) via a search query---to provide their users with a more satisfactory search experience. The record (or history) of users' past interactions serves as a valuable asset to achieve personalization. While user history data can span over a long period of time, only a part of the history is relevant to a user's current search intent. Moreover, since historical interactions take place at aperiodic points in time, modeling their relevance to the current search query entangles complex temporal dependencies. We propose multi-resolution attention to address these challenges for personalized item search. Our approach captures higher-order temporal relations between user queries and their history across several temporal subspaces (i.e., resolutions), each corresponding to distinct temporal ranges with adaptive time boundaries that are also learned directly from data. We achieve this by coupling the conventional multi-head attention module with a differentiable soft-thresholding mechanism, which essentially operates as a masking function in the temporal domain. Comparisons with strong baselines on an open-source benchmark dataset confirm the efficacy of our approach.

[1]  Fuzheng Zhang,et al.  Structural Relationship Representation Learning with Graph Embedding for Personalized Product Search , 2020, CIKM.

[2]  Oren Kurland,et al.  Query Reformulation in E-Commerce Search , 2020, SIGIR.

[3]  Xiaoling Wang,et al.  Sequential Recommender via Time-aware Attentive Memory Network , 2020, CIKM.

[4]  Xueming Qian,et al.  Personalized product search based on user transaction history and hypergraph learning , 2020, Multimedia Tools and Applications.

[5]  W. Bruce Croft,et al.  Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search , 2020, SIGIR.

[6]  Heng-Tze Cheng,et al.  End-to-End Deep Attentive Personalized Item Retrieval for Online Content-sharing Platforms , 2020, WWW.

[7]  Mounia Lalmas,et al.  Algorithmic Effects on the Diversity of Consumption on Spotify , 2020, WWW.

[8]  Hongning Wang,et al.  Déjà vu: A Contextualized Temporal Attention Mechanism for Sequential Recommendation , 2020, WWW.

[9]  Yujie Wang,et al.  Time Interval Aware Self-Attention for Sequential Recommendation , 2020, WSDM.

[10]  Zaiqiao Meng,et al.  Dynamic Bayesian Metric Learning for Personalized Product Search , 2019, CIKM.

[11]  Jianmo Ni,et al.  Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects , 2019, EMNLP.

[12]  Da Xu,et al.  Self-attention with Functional Time Representation Learning , 2019, NeurIPS.

[13]  W. Bruce Croft,et al.  A Zero Attention Model for Personalized Product Search , 2019, CIKM.

[14]  Chen Ma,et al.  Hierarchical Gating Networks for Sequential Recommendation , 2019, KDD.

[15]  Peng Jiang,et al.  BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer , 2019, CIKM.

[16]  Sudarshan Lamkhede,et al.  Challenges in Search on Streaming Services: Netflix Case Study , 2019, SIGIR.

[17]  Mohan S. Kankanhalli,et al.  Attentive Long Short-Term Preference Modeling for Personalized Product Search , 2018, ACM Trans. Inf. Syst..

[18]  Julian J. McAuley,et al.  Self-Attentive Sequential Recommendation , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[19]  Haibin Cheng,et al.  Real-time Personalization using Embeddings for Search Ranking at Airbnb , 2018, KDD.

[20]  Edward Y. Chang,et al.  Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks , 2018, SIGIR.

[21]  Mohit Sharma,et al.  A Taxonomy of Queries for E-commerce Search , 2018, SIGIR.

[22]  Ashish Vaswani,et al.  Self-Attention with Relative Position Representations , 2018, NAACL.

[23]  Yiqun Liu,et al.  User Intent, Behaviour, and Perceived Satisfaction in Product Search , 2018, WSDM.

[24]  Yongfeng Zhang,et al.  Sequential Recommendation with User Memory Networks , 2018, WSDM.

[25]  Tara N. Sainath,et al.  State-of-the-Art Speech Recognition with Sequence-to-Sequence Models , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[26]  Jure Leskovec,et al.  Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time , 2017, WWW.

[27]  W. Bruce Croft,et al.  Learning a Hierarchical Embedding Model for Personalized Product Search , 2017, SIGIR.

[28]  Deng Cai,et al.  What to Do Next: Modeling User Behaviors by Time-LSTM , 2017, IJCAI.

[29]  Samy Bengio,et al.  Time-Dependent Representation for Neural Event Sequence Prediction , 2017, ICLR.

[30]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[31]  Guokun Lai,et al.  Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks , 2017, SIGIR.

[32]  Hongyuan Mei,et al.  The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process , 2016, NIPS.

[33]  Paul Covington,et al.  Deep Neural Networks for YouTube Recommendations , 2016, RecSys.

[34]  M. de Rijke,et al.  Learning Latent Vector Spaces for Product Search , 2016, CIKM.

[35]  Marie-Francine Moens,et al.  Monolingual and Cross-Lingual Information Retrieval Models Based on (Bilingual) Word Embeddings , 2015, SIGIR.

[36]  Kenneth Wai-Ting Leung,et al.  Collaborative personalized Twitter search with topic-language models , 2014, SIGIR.

[37]  Iván Cantador,et al.  Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols , 2013, User Modeling and User-Adapted Interaction.

[38]  Ryen W. White,et al.  Probabilistic models for personalizing web search , 2012, WSDM '12.

[39]  Filip Radlinski,et al.  Personalizing web search using long term browsing history , 2011, WSDM '11.

[40]  Brian Harmer,et al.  YouTube: Online Video and Participatory Culture , 2010 .

[41]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.

[42]  J. Rowley.  Product search in e‐shopping: a review and research propositions , 2000 .

[43]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[44]  Jason Eisner,et al.  The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process , 2017 .

[45]  Wendy W. Moe,et al.  The Influence of Goal‐Directed and Experiential Activities on Online Flow Experiences , 2003 .