NAIS: Neural Attentive Item Similarity Model for Recommendation

Abstract

Item-to-item collaborative filtering (aka. item-based CF) has been long used for building recommender systems in industrial settings, owing to its interpretability and efficiency in real-time personalization. It builds a user's profile as her historically interacted items, recommending new items that are similar to the user's profile. As such, the key to an item-based CF method is in the estimation of item similarities. Early approaches use statistical measures such as cosine similarity and Pearson coefficient to estimate item similarities, which are less accurate since they lack tailored optimization for the recommendation task. In recent years, several works attempt to learn item similarities from data, by expressing the similarity as an underlying model and estimating model parameters by optimizing a recommendation-aware objective function. While extensive efforts have been made to use shallow linear models for learning item similarities, there has been relatively less work exploring nonlinear neural network models for item-based CF. In this work, we propose a neural network model named Neural Attentive Item Similarity model (NAIS) for item-based CF. The key to our design of NAIS is an attention network, which is capable of distinguishing which historical items in a user profile are more important for a prediction. Compared to the state-of-the-art item-based CF method Factored Item Similarity Model (FISM), our NAIS has stronger representation power with only a few additional parameters brought by the attention network. Extensive experiments on two public benchmarks demonstrate the effectiveness of NAIS. This work is the first attempt that designs neural network models for item-based CF, opening up new research possibilities for future developments of neural recommender systems.

References in corpus (5)

• Neural Machine Translation by Jointly Learning to Align and Translate
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Adversarial Personalized Ranking for Recommendation
• Item Silk Road: Recommending Items from Information Domains to Social Users
• Related Pins at Pinterest: The Evolution of a Real-World Recommender System

Cited by in corpus (68)

• KGAT: Knowledge Graph Attention Network for Recommendation
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• Attentive Aspect Modeling for Review-aware Recommendation
• Elliot: a Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation
• FedRecAttack: Model Poisoning Attack to Federated Recommendation
• A Hierarchical Attention Model for Social Contextual Image Recommendation
• On the Effectiveness of Sampled Softmax Loss for Item Recommendation
• Time Interval-enhanced Graph Neural Network for Shared-account Cross-domain Sequential Recommendation
• Reinforcement Learning-enhanced Shared-account Cross-domain Sequential Recommendation
• Next Item Recommendation with Self-Attention
• DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation
• Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
• Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction
• Towards a Robust Deep Neural Network in Texts: A Survey
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Local Collaborative Autoencoders
• Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation
• Adaptive Collaborative Filtering with Personalized Time Decay Functions for Financial Product Recommendation
• RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation
• Feature Re-Learning with Data Augmentation for Video Relevance Prediction
• CATA++: A Collaborative Dual Attentive Autoencoder Method for Recommending Scientific Articles
• Quaternion-Based Self-Attentive Long Short-Term User Preference Encoding for Recommendation
• NGAT4Rec: Neighbor-Aware Graph Attention Network For Recommendation
• Boosting Item-based Collaborative Filtering via Nearly Uncoupled Random Walks
• Modelling High-Order Social Relations for Item Recommendation
• Hierarchical Fashion Graph Network for Personalized Outfit Recommendation
• Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems
• Adversarial Training Towards Robust Multimedia Recommender System
• LogicRec: Recommendation with Users' Logical Requirements
• Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
• LT-OCF: Learnable-Time ODE-based Collaborative Filtering
• Improving End-to-End Sequential Recommendations with Intent-aware Diversification
• Unbiased and Robust: External Attention-enhanced Graph Contrastive Learning for Cross-domain Sequential Recommendation
• Lightweight yet Efficient: An External Attentive Graph Convolutional Network with Positional Prompts for Sequential Recommendation
• Knowledge-Enhanced Recommendation with User-Centric Subgraph Network
• Modeling Embedding Dimension Correlations via Convolutional Neural Collaborative Filtering
• Sparse Neural Attentive Knowledge-based Models for Grade Prediction
• AttnMove: History Enhanced Trajectory Recovery via Attentional Network
• An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation
• A^2-GCN: An Attribute-aware Attentive GCN Model for Recommendation
• Self-Attentive Neural Collaborative Filtering
• Sampler Design for Implicit Feedback Data by Noisy-label Robust Learning
• User Embedding based Neighborhood Aggregation Method for Inductive Recommendation
• Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View
• Represent Items by Items: An Enhanced Representation of the Target Item for Recommendation
• Deep Unified Representation for Heterogeneous Recommendation
• Explore User Neighborhood for Real-time E-commerce Recommendation
• Deep Item-based Collaborative Filtering for Top-N Recommendation
• NAIRS: A Neural Attentive Interpretable Recommendation System
• Interest-Related Item Similarity Model Based on Multimodal Data for Top-N Recommendation
• Addressing Time Bias in Bipartite Graph Ranking for Important Node Identification
• Context-aware Non-linear and Neural Attentive Knowledge-based Models for Grade Prediction
• BCFNet: A Balanced Collaborative Filtering Network with Attention Mechanism
• Spectrum-enhanced Pairwise Learning to Rank
• PAS: A Position-Aware Similarity Measurement for Sequential Recommendation
• Path-based Deep Network for Candidate Item Matching in Recommenders
• Dual-embedding based Neural Collaborative Filtering for Recommender Systems
• Large-scale Real-time Personalized Similar Product Recommendations
• Convolutional Gaussian Embeddings for Personalized Recommendation with Uncertainty
• Personalized Multimedia Item and Key Frame Recommendation
• Visually-aware Recommendation with Aesthetic Features
• Consistency-Aware Recommendation for User-Generated ItemList Continuation
• Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation
• Quaternion-Based Graph Convolution Network for Recommendation