The study of consumer psychology reveals two categories of consumption decision procedures: compensatory rules and non-compensatory rules. Existing recommendation models which are based on latent factor models assume the consumers follow the compensatory rules, i.e. they evaluate an item over multip... || Bradley-Terry Model; 偏好结构；decision procesison； 非线性加权; || Chen Lin...
Matrix Factorization (MF) is widely used in Recommender Systems (RSs) for estimating missing ratings in the rating matrix. MF faces major challenges of handling very sparse and large data. Poisson Factorization (PF) as an MF variant addresses these challenges with high efficiency by only computing o... || Poisson Factorization; content-based + CF; Gamma; graphical models; VI (Variational Inference)；属性集合; || Trong Dinh Thac Do...
Recommending a point-of-interest (POI) a user will visit next based on temporal and spatial context information is an important task in mobile-based applications. Recently, several POI recommendation models based on conventional sequential-data modeling approaches have been proposed. However, such m... || embedding learning; word2vec; content based; POI; skip-gram； 初始化隐向量; || Buru Chang...
Our interactions with an application frequently leave a heterogeneous and contemporaneous trail of actions and adoptions (e.g., clicks, bookmarks, pur- chases). Given a sequence of a particular type (e.g., purchases)– referred to as the target sequence, we seek to predict the next item expected to a... || LSTM; Cross domain; next-item; Siamese networks; || Duc-Trong Le, Hady W. Lauw and Yuan Fang...
Neural Machine Translation (NMT) has drawn much attention due to its promising translation performance recently. However, several studies indicate that NMT often generates fluent but unfaithful translations. In this paper, we propose a method to alleviate this problem by using a phrase table as reco... || stacked LSTM; 规则结合ML；; || Yang Zhao...
User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 107, results in expensive storage and computational cost. This prohibits fast recommendation especially on mobile applications where the comp... || FM; discrete; content-based; || Han Liu; Xiangnan He...
Non-IID recommender system discloses the nature of recommendation and has shown its potential in improving recommendation quality and addressing issues such as sparsity and cold start. It leverages existing work that usually treats users/items as independent while ignoring the rich couplings within ... || non-IID; content based; CF based; CNN; NCF; || Quangui Zhang; Longbing Cao...
A significant problem of recommender systems is their inability to explain recommendations, resulting in turn in ineffective feedback from users and the inability to adapt to users’ preferences. We propose a hybrid method for calculating predicted ratings, built upon an item/aspect-based graph with ... || interpretation; A-I model; aspect-item model；可解释性；memory based; memory-based；公式很漂亮; || Antonio Rago, Oana Cocarascu, Francesca Toni...
Network embedding has been recently used in social network recommendations by embedding low- dimensional representations of network items for recommendation. However, existing item recommendation models in social networks suffer from two limitations. First, these models partially use item informati... || point-wise recommendation; 多信息融合； random walk; || Li Gao...
Cross-network recommender systems use auxiliary information from multiple source networks to create holistic user profiles and improve recommendations in a target network. However, we find two major limitations in existing cross-network solutions that reduce overall recommender performance. Existing... || Cross-domain; LSTM: attention model; next-item recommendation; || Dilruk Perera and Roger Zimmermann...
