Explore User Neighborhood for Real-time E-commerce Recommendation

  title={Explore User Neighborhood for Real-time E-commerce Recommendation},
  author={Xu Xie and Fei Sun and Xiaoyong Yang and Zhao Yang and Jinyang Gao and Wenwu Ou and Bin Cui},
  journal={2021 IEEE 37th International Conference on Data Engineering (ICDE)},
  • Xu XieFei Sun Bin Cui
  • Published 28 February 2021
  • Computer Science
  • 2021 IEEE 37th International Conference on Data Engineering (ICDE)
Recommender systems play a vital role in modern online services, such as Amazon and Taobao. Traditional personalized methods, which focus on user-item (UI) relations, have been widely applied in industrial settings, owing to their efficiency and effectiveness. Despite their success, we argue that these approaches ignore local information hidden in similar users. To tackle this problem, user-based methods exploit similar user relations to make recommendations in a local perspective. Nevertheless… 

Figures and Tables from this paper

Serenade - Low-Latency Session-Based Recommendation in e-Commerce at Scale

VMIS-kNN is proposed, an adaptation of a state-of-the-art nearest neighbor approach to session-based recommendation, which leverages a prebuilt index to compute next-item recommendations with low latency in scenarios with hundreds of millions of clicks to search through.

Efficient and Scalable Recommendation via Item-Item Graph Partitioning

A recursive graph partitioning strategy is proposed to ensure that the item set is divided into several partitions of finite size, which allows ERGP to have guaranteed efficiency and high scalability when the number of items increases.

Graph Neural Networks in Recommender Systems: A Survey

This article provides a taxonomy of GNN-based recommendation models according to the types of information used and recommendation tasks and systematically analyze the challenges of applying GNN on different types of data.

CausCF: Causal Collaborative Filtering for Recommendation Effect Estimation

The proposed CausCF extends the classical matrix factorization to the tensor factorization with three dimensions---user, item, and treatment and employs regression discontinuity design (RDD) to evaluate the precision of the estimated causal effects from different models.

Refining Graph Representation for Cross-domain Recommendation Based on Edge Pruning in Latent Space

This paper introduces edge pruning into the latest graph-based CDR method to refine graph representation and introduces a state-of-the-art graph neural network into the graph construction of the proposed method that considers the interactions between users and items thereby obtaining effective embedding features in a domain.

Proactively Control Privacy in Recommender Systems

A privacy aware recommendation framework that gives users delicate control over their personal data, including implicit behaviors, e.g., clicks and watches, and shows that the proposed framework can effectively protect users’ privacy since they can obtain comparable or even better results with much less disclosed data.

Studying the Impact of Data Disclosure Mechanism in Recommender Systems via Simulation

This paper proposes a privacy aware recommendation framework that gives users fine control over their data, and studies the impact of different data disclosure mechanisms via simulation with reinforcement learning due to the high cost of real-world experiments.

Heterogeneity-Aware Distributed Machine Learning Training via Partial Reduce

A novel variant of all-reduction, called partial-reduce, is proposed, which provides high heterogeneity tolerance and performance by decomposing the synchronous all- reduce primitive into parallel-asynchronous partial-Reduce operations.

BlindFL: Vertical Federated Machine Learning without Peeking into Your Data

BlindFL is introduced, a novel framework for VFL training and inference that addresses the functionality and security of ML modes in the VFL scenario, and carefully analyzes the security during the federated execution and formalizes the privacy requirements.

Assimilation and Contrast: The Two-sided Anchoring Effects of Recommender Systems

Previous studies on the behavioral implications of recommender systems suggest that consumer preferences after consumption are malleable and tend to shift towards the ratings presented by a



Factorization meets the neighborhood: a multifaceted collaborative filtering model

The factor and neighborhood models can now be smoothly merged, thereby building a more accurate combined model and a new evaluation metric is suggested, which highlights the differences among methods, based on their performance at a top-K recommendation task.

Practical Linear Models for Large-Scale One-Class Collaborative Filtering

It is shown that it is possible to scale up linear recommenders to big data by learning an OCCF model in a randomized low-dimensional embedding of the user-item interaction matrix.

On the Effectiveness of Linear Models for One-Class Collaborative Filtering

LRec is proposed, a variant of SLIM that overcomes limitations without sacrificing any ofSLIM's strengths and consistently and significantly outperforms all existing methods on a range of datasets.

Session-based Recommendations with Recurrent Neural Networks

It is argued that by modeling the whole session, more accurate recommendations can be provided by an RNN-based approach for session-based recommendations, and introduced several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem.

Multi-Interest Network with Dynamic Routing for Recommendation at Tmall

This paper designs a multi-interest extractor layer based on the recently proposed dynamic routing mechanism, which is applicable for modeling and extracting diverse interests from user's behaviors, and proposes a technique named label-aware attention to help the learning process of user representations.

Local Item-Item Models For Top-N Recommendation

This work presents a method that computes the prediction scores as a user-specific combination of the predictions derived by a global and local item-item models that improves upon the standard SLIM model and outperforms competing top-N recommendation approaches.

Item-based top-N recommendation algorithms

This article presents one class of model-based recommendation algorithms that first determines the similarities between the various items and then uses them to identify the set of items to be recommended, and shows that these item-based algorithms are up to two orders of magnitude faster than the traditional user-neighborhood based recommender systems and provide recommendations with comparable or better quality.

Self-Attentive Sequential Recommendation

Extensive empirical studies show that the proposed self-attention based sequential model (SASRec) outperforms various state-of-the-art sequential models (including MC/CNN/RNN-based approaches) on both sparse and dense datasets.

Translation-based Recommendation

This paper proposes a unified method, TransRec, to model such third-order relationships for large-scale sequential prediction, and embeds items into a 'transition space' where users are modeled as translation vectors operating on item sequences.

Mind the gaps: weighting the unknown in large-scale one-class collaborative filtering

This paper proposes two novel algorithms for large-scale OCCF that allow to weight the unknowns: Low-rank matrix approximation, probabilistic latent semantic analysis, and maximum-margin matrix factorization.