Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Recommendation": models, code, and papers

A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations

Apr 03, 2022
Krishna Prasad Neupane, Ervine Zheng, Yu Kong, Qi Yu

We present a novel dynamic recommendation model that focuses on users who have interactions in the past but turn relatively inactive recently. Making effective recommendations to these time-sensitive cold-start users is critical to maintain the user base of a recommender system. Due to the sparse recent interactions, it is challenging to capture these users' current preferences precisely. Solely relying on their historical interactions may also lead to outdated recommendations misaligned with their recent interests. The proposed model leverages historical and current user-item interactions and dynamically factorizes a user's (latent) preference into time-specific and time-evolving representations that jointly affect user behaviors. These latent factors further interact with an optimized item embedding to achieve accurate and timely recommendations. Experiments over real-world data help demonstrate the effectiveness of the proposed time-sensitive cold-start recommendation model.

* 7 pages, conference 

  Access Paper or Ask Questions

RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation

Nov 19, 2021
Chenglin Li, Mingjun Zhao, Huanming Zhang, Chenyun Yu, Lei Cheng, Guoqiang Shu, Beibei Kong, Di Niu

Cross-domain recommendation can help alleviate the data sparsity issue in traditional sequential recommender systems. In this paper, we propose the RecGURU algorithm framework to generate a Generalized User Representation (GUR) incorporating user information across domains in sequential recommendation, even when there is minimum or no common users in the two domains. We propose a self-attentive autoencoder to derive latent user representations, and a domain discriminator, which aims to predict the origin domain of a generated latent representation. We propose a novel adversarial learning method to train the two modules to unify user embeddings generated from different domains into a single global GUR for each user. The learned GUR captures the overall preferences and characteristics of a user and thus can be used to augment the behavior data and improve recommendations in any single domain in which the user is involved. Extensive experiments have been conducted on two public cross-domain recommendation datasets as well as a large dataset collected from real-world applications. The results demonstrate that RecGURU boosts performance and outperforms various state-of-the-art sequential recommendation and cross-domain recommendation methods. The collected data will be released to facilitate future research.

* 11 pages, 2 figures, 4 tables, Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining 

  Access Paper or Ask Questions

Enhancing Top-N Item Recommendations by Peer Collaboration

Dec 02, 2021
Yang Sun, Fajie Yuan, Min Yang, Alexandros Karatzoglou, Shen Li, Xiaoyan Zhao

Deep neural networks (DNN) have achieved great success in the recommender systems (RS) domain. However, to achieve remarkable performance, DNN-based recommender models often require numerous parameters, which inevitably bring redundant neurons and weights, a phenomenon referred to as over-parameterization. In this paper, we plan to exploit such redundancy phenomena to improve the performance of RS. Specifically, we propose PCRec, a top-N item \underline{rec}ommendation framework that leverages collaborative training of two DNN-based recommender models with the same network structure, termed \underline{p}eer \underline{c}ollaboration. PCRec can reactivate and strengthen the unimportant (redundant) weights during training, which achieves higher prediction accuracy but maintains its original inference efficiency. To realize this, we first introduce two criteria to identify the importance of weights of a given recommender model. Then, we rejuvenate the unimportant weights by transplanting outside information (i.e., weights) from its peer network. After such an operation and retraining, the original recommender model is endowed with more representation capacity by possessing more functional model parameters. To show its generality, we instantiate PCRec by using three well-known recommender models. We conduct extensive experiments on three real-world datasets, and show that PCRec yields significantly better recommendations than its counterpart with the same model (parameter) size.

* 9 pages, 6 figures 

  Access Paper or Ask Questions

KECRS: Towards Knowledge-Enriched Conversational Recommendation System

May 18, 2021
Tong Zhang, Yong Liu, Peixiang Zhong, Chen Zhang, Hao Wang, Chunyan Miao

The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions. To better understand user's intentions, external knowledge graphs (KG) have been introduced into chit-chat-based CRS. However, existing chit-chat-based CRS usually generate repetitive item recommendations, and they cannot properly infuse knowledge from KG into CRS to generate informative responses. To remedy these issues, we first reformulate the conversational recommendation task to highlight that the recommended items should be new and possibly interested by users. Then, we propose the Knowledge-Enriched Conversational Recommendation System (KECRS). Specifically, we develop the Bag-of-Entity (BOE) loss and the infusion loss to better integrate KG with CRS for generating more diverse and informative responses. BOE loss provides an additional supervision signal to guide CRS to learn from both human-written utterances and KG. Infusion loss bridges the gap between the word embeddings and entity embeddings by minimizing distances of the same words in these two embeddings. Moreover, we facilitate our study by constructing a high-quality KG, \ie The Movie Domain Knowledge Graph (TMDKG). Experimental results on a large-scale dataset demonstrate that KECRS outperforms state-of-the-art chit-chat-based CRS, in terms of both recommendation accuracy and response generation quality.

  Access Paper or Ask Questions

Algorithms and Architecture for Real-time Recommendations at News UK

Sep 15, 2017
Dion Bailey, Tom Pajak, Daoud Clarke, Carlos Rodriguez

Recommendation systems are recognised as being hugely important in industry, and the area is now well understood. At News UK, there is a requirement to be able to quickly generate recommendations for users on news items as they are published. However, little has been published about systems that can generate recommendations in response to changes in recommendable items and user behaviour in a very short space of time. In this paper we describe a new algorithm for updating collaborative filtering models incrementally, and demonstrate its effectiveness on clickstream data from The Times. We also describe the architecture that allows recommendations to be generated on the fly, and how we have made each component scalable. The system is currently being used in production at News UK.

* Accepted for presentation at AI-2017 Thirty-seventh SGAI International Conference on Artificial Intelligence. Cambridge, England 12-14 December 2017 

  Access Paper or Ask Questions

Learning Elastic Embeddings for Customizing On-Device Recommenders

Jun 04, 2021
Tong Chen, Hongzhi Yin, Yujia Zheng, Zi Huang, Yang Wang, Meng Wang

In today's context, deploying data-driven services like recommendation on edge devices instead of cloud servers becomes increasingly attractive due to privacy and network latency concerns. A common practice in building compact on-device recommender systems is to compress their embeddings which are normally the cause of excessive parameterization. However, despite the vast variety of devices and their associated memory constraints, existing memory-efficient recommender systems are only specialized for a fixed memory budget in every design and training life cycle, where a new model has to be retrained to obtain the optimal performance while adapting to a smaller/larger memory budget. In this paper, we present a novel lightweight recommendation paradigm that allows a well-trained recommender to be customized for arbitrary device-specific memory constraints without retraining. The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function. Correspondingly, we propose an innovative approach, namely recommendation with universally learned elastic embeddings (RULE). To ensure the expressiveness of all candidate embedding blocks, RULE enforces a diversity-driven regularization when learning different embedding blocks. Then, a performance estimator-based evolutionary search function is designed, allowing for efficient specialization of elastic embeddings under any memory constraint for on-device recommendation. Extensive experiments on real-world datasets reveal the superior performance of RULE under tight memory budgets.

* To appear in KDD'21 

  Access Paper or Ask Questions

Lightweight Self-Attentive Sequential Recommendation

Aug 25, 2021
Yang Li, Tong Chen, Peng-Fei Zhang, Hongzhi Yin

Modern deep neural networks (DNNs) have greatly facilitated the development of sequential recommender systems by achieving state-of-the-art recommendation performance on various sequential recommendation tasks. Given a sequence of interacted items, existing DNN-based sequential recommenders commonly embed each item into a unique vector to support subsequent computations of the user interest. However, due to the potentially large number of items, the over-parameterised item embedding matrix of a sequential recommender has become a memory bottleneck for efficient deployment in resource-constrained environments, e.g., smartphones and other edge devices. Furthermore, we observe that the widely-used multi-head self-attention, though being effective in modelling sequential dependencies among items, heavily relies on redundant attention units to fully capture both global and local item-item transition patterns within a sequence. In this paper, we introduce a novel lightweight self-attentive network (LSAN) for sequential recommendation. To aggressively compress the original embedding matrix, LSAN leverages the notion of compositional embeddings, where each item embedding is composed by merging a group of selected base embedding vectors derived from substantially smaller embedding matrices. Meanwhile, to account for the intrinsic dynamics of each item, we further propose a temporal context-aware embedding composition scheme. Besides, we develop an innovative twin-attention network that alleviates the redundancy of the traditional multi-head self-attention while retaining full capacity for capturing long- and short-term (i.e., global and local) item dependencies. Comprehensive experiments demonstrate that LSAN significantly advances the accuracy and memory efficiency of existing sequential recommenders.

  Access Paper or Ask Questions

PAS: A Position-Aware Similarity Measurement for Sequential Recommendation

May 14, 2022
Zijie Zeng, Jing Lin, Weike Pan, Zhong Ming, Zhongqi Lu

The common item-based collaborative filtering framework becomes a typical recommendation method when equipped with a certain item-to-item similarity measurement. On one hand, we realize that a well-designed similarity measurement is the key to providing satisfactory recommendation services. On the other hand, similarity measurements designed for sequential recommendation are rarely studied by the recommender systems community. Hence in this paper, we focus on devising a novel similarity measurement called position-aware similarity (PAS) for sequential recommendation. The proposed PAS is, to our knowledge, the first count-based similarity measurement that concurrently captures the sequential patterns from the historical user behavior data and from the item position information within the input sequences. We conduct extensive empirical studies on four public datasets, in which our proposed PAS-based method exhibits competitive performance even compared to the state-of-the-art sequential recommendation methods, including a very recent similarity-based method and two GNN-based methods.

* International Joint Conference on Neural Networks (IJCNN 2022, Padua, Italy), 8 pages, Camera-Ready Version 

  Access Paper or Ask Questions

A survey of recommender systems for energy efficiency in buildings: Principles, challenges and prospects

Feb 09, 2021
Yassine Himeur, Abdullah Alsalemi, Ayman Al-Kababji, Faycal Bensaali, Abbes Amira, Christos Sardianos, George Dimitrakopoulos, Iraklis Varlamis

Recommender systems have significantly developed in recent years in parallel with the witnessed advancements in both internet of things (IoT) and artificial intelligence (AI) technologies. Accordingly, as a consequence of IoT and AI, multiple forms of data are incorporated in these systems, e.g. social, implicit, local and personal information, which can help in improving recommender systems' performance and widen their applicability to traverse different disciplines. On the other side, energy efficiency in the building sector is becoming a hot research topic, in which recommender systems play a major role by promoting energy saving behavior and reducing carbon emissions. However, the deployment of the recommendation frameworks in buildings still needs more investigations to identify the current challenges and issues, where their solutions are the keys to enable the pervasiveness of research findings, and therefore, ensure a large-scale adoption of this technology. Accordingly, this paper presents, to the best of the authors' knowledge, the first timely and comprehensive reference for energy-efficiency recommendation systems through (i) surveying existing recommender systems for energy saving in buildings; (ii) discussing their evolution; (iii) providing an original taxonomy of these systems based on specified criteria, including the nature of the recommender engine, its objective, computing platforms, evaluation metrics and incentive measures; and (iv) conducting an in-depth, critical analysis to identify their limitations and unsolved issues. The derived challenges and areas of future implementation could effectively guide the energy research community to improve the energy-efficiency in buildings and reduce the cost of developed recommender systems-based solutions.

* Information Fusion 2021 
* 35 pages, 11 figures, 1 table 

  Access Paper or Ask Questions