【推薦系統】推薦系統領域最新研究進展

本文精選了上周（1024-1030）最新釋出的17篇推薦系統相關論文。

本次論文集合的方向主要包括可解釋性推薦[1]、基于強化學習的推薦算法[2]、深度混合推薦算法[4]、序列化推薦[5,8,15,16]、自監督推薦算法[10]、基于量子計算的因子分解機推薦[11]、魯棒推薦算法[12,13]、基于隐私保護的推薦算法[14]等。

以下整理了論文标題以及摘要，如感興趣可移步原文精讀。

• 1. COFFEE: Counterfactual Fairness for Personalized Text Generation in  Explainable Recommendation
• 2. Fine-Grained Session Recommendations in E-commerce using Deep  Reinforcement Learning
• 3. Taxonomic Recommendations of Real Estate Properties with Textual  Attribute Information
• 4. Deep Latent Mixture Model for Recommendation
• 5. Disentangling Past-Future Modeling in Sequential Recommendation via Dual  Networks
• 6. Empowering Long-tail Item Recommendation through Cross Decoupling  Network (CDN)
• 7. Goal-Driven Context-Aware Next Service Recommendation for Mashup  Composition
• 8. Sequential Recommendation with Auxiliary Item Relationships via  Multi-Relational Transformer
• 9. Coupling User Preference with External Rewards to Enable Driver-centered  and Resource-aware EV Charging Recommendation
• 10. Self-supervised Graph-based Point-of-interest Recommendation
• 11. Implementation of Trained Factorization Machine Recommendation System on  Quantum Annealer
• 12. Triplet Losses-based Matrix Factorization for Robust Recommendations
• 13. Towards Robust Recommender Systems via Triple Cooperative Defense
• 14. FedGRec: Federated Graph Recommender System with Lazy Update of Latent  Embeddings
• 15. Heterogeneous Information Crossing on Graphs for Session-based  Recommender Systems
• 16. Learning Vector-Quantized Item Representation for Transferable  Sequential Recommenders
• 17. Towards Employing Recommender Systems for Supporting Data and Algorithm  Sharing

1. COFFEE: Counterfactual Fairness for Personalized Text Generation in  Explainable Recommendation

Nan Wang, Shaoliang Nie, Qifan Wang, Yi-Chia Wang, Maziar Sanjabi, Jingzhou Liu, Hamed Firooz, Hongning Wang

​​https://arxiv.org/abs/2210.15500​​

Personalized text generation has broad industrial applications, such as explanation generation for recommendations, conversational systems, etc. Personalized text generators are usually trained on user written text, e.g., reviews collected on e-commerce platforms. However, due to historical, social, or behavioral reasons, there may exist bias that associates certain linguistic quality of user written text with the users' protected attributes such as gender, race, etc. The generators can identify and inherit these correlations and generate texts discriminately w.r.t. the users' protected attributes. Without proper intervention, such bias can adversarially influence the users' trust and reliance on the system. From a broader perspective, bias in auto-generated contents can reinforce the social stereotypes about how online users write through interactions with the users.

2. Fine-Grained Session Recommendations in E-commerce using Deep  Reinforcement Learning

Diddigi Raghu Ram Bharadwaj, Lakshya Kumar, Saif Jawaid, Sreekanth Vempati

​​https://arxiv.org/abs/2210.15451​​

Sustaining users' interest and keeping them engaged in the platform is very important for the success of an e-commerce business. A session encompasses different activities of a user between logging into the platform and logging out or making a purchase. User activities in a session can be classified into two groups: Known Intent and Unknown intent. Known intent activity pertains to the session where the intent of a user to browse/purchase a specific product can be easily captured. Whereas in unknown intent activity, the intent of the user is not known. For example, consider the scenario where a user enters the session to casually browse the products over the platform, similar to the window shopping experience in the offline setting. While recommending similar products is essential in the former, accurately understanding the intent and recommending interesting products is essential in the latter setting in order to retain a user. In this work, we focus primarily on the unknown intent setting where our objective is to recommend a sequence of products to a user in a session to sustain their interest, keep them engaged and possibly drive them towards purchase. We formulate this problem in the framework of the Markov Decision Process (MDP), a popular mathematical framework for sequential decision making and solve it using Deep Reinforcement Learning (DRL) techniques. However, training the next product recommendation is difficult in the RL paradigm due to large variance in browse/purchase behavior of the users. Therefore, we break the problem down into predicting various product attributes, where a pattern/trend can be identified and exploited to build accurate models. We show that the DRL agent provides better performance compared to a greedy strategy.

3. Taxonomic Recommendations of Real Estate Properties with Textual  Attribute Information

Zachary Harrison, Anish Khazane

​​https://arxiv.org/abs/2210.15142​​

In this extended abstract, we present an end to end approach for building a taxonomy of home attribute terms that enables hierarchical recommendations of real estate properties. We cover the methodology for building a real-estate taxonomy, metrics for measuring this structure's quality, and then conclude with a production use-case of making recommendations from search keywords at different levels of topical similarity.

4. Deep Latent Mixture Model for Recommendation

Jun Zhang, Ping Li, Wei Wang

​​https://arxiv.org/abs/2210.15112​​

Recent advances in neural networks have been successfully applied to many tasks in online recommendation applications. We propose a new framework called cone latent mixture model which makes use of hand-crafted state being able to factor distinct dependencies among multiple related documents. Specifically, it uses discriminative optimization techniques in order to generate effective multi-level knowledge bases, and uses online discriminative learning techniques in order to leverage these features. And for this joint model which uses confidence estimates for each topic and is able to learn a discriminatively trained jointly to automatically extracted salient features where discriminative training is only uses features and then is able to accurately trained.

5. Disentangling Past-Future Modeling in Sequential Recommendation via Dual  Networks

Hengyu Zhang, Enming Yuan, Wei Guo, Zhicheng He, Jiarui Qin, Huifeng Guo, Bo Chen, Xiu Li, Ruiming Tang

​​https://arxiv.org/abs/2210.14577​​

Sequential recommendation (SR) plays an important role in personalized recommender systems because it captures dynamic and diverse preferences from users' real-time increasing behaviors. Unlike the standard autoregressive training strategy, future data (also available during training) has been used to facilitate model training as it provides richer signals about user's current interests and can be used to improve the recommendation quality. However, these methods suffer from a severe training-inference gap, i.e., both past and future contexts are modeled by the same encoder when training, while only historical behaviors are available during inference. This discrepancy leads to potential performance degradation. To alleviate the training-inference gap, we propose a new framework DualRec, which achieves past-future disentanglement and past-future mutual enhancement by a novel dual network. Specifically, a dual network structure is exploited to model the past and future context separately. And a bi-directional knowledge transferring mechanism enhances the knowledge learnt by the dual network. Extensive experiments on four real-world datasets demonstrate the superiority of our approach over baseline methods. Besides, we demonstrate the compatibility of DualRec by instantiating using RNN, Transformer, and filter-MLP as backbones. Further empirical analysis verifies the high utility of modeling future contexts under our DualRec framework.

6. Empowering Long-tail Item Recommendation through Cross Decoupling  Network (CDN)

Yin Zhang, Ruoxi Wang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyang Yi, Lichan Hong, James Caverlee, Ed H. Chi

​​https://arxiv.org/abs/2210.14309​​

Recommenders provide personalized content recommendations to users. They often suffer from highly skewed long-tail item distributions, with a small fraction of the items receiving most of the user feedback. This hurts model quality especially for the slices without much supervision. Existing work in both academia and industry mainly focuses on re-balancing strategies (e.g., up-sampling and up-weighting), leveraging content features, and transfer learning. However, there still lacks of a deeper understanding of how the long-tail distribution influences the recommendation performance.

7. Goal-Driven Context-Aware Next Service Recommendation for Mashup  Composition

Xihao Xie, Jia Zhang, Rahul Ramachandran, Tsengdar J. Lee, Seungwon Lee

​​https://arxiv.org/abs/2210.14127​​

As service-oriented architecture becoming one of the most prevalent techniques to rapidly deliver functionalities to customers, increasingly more reusable software components have been published online in forms of web services. To create a mashup, it gets not only time-consuming but also error-prone for developers to find suitable services from such a sea of services. Service discovery and recommendation has thus attracted significant momentum in both academia and industry. This paper proposes a novel incremental recommend-as-you-go approach to recommending next potential service based on the context of a mashup under construction, considering services that have been selected to the current step as well as its mashup goal. The core technique is an algorithm of learning the embedding of services, which learns their past goal-driven context-aware decision making behaviors in addition to their semantic descriptions and co-occurrence history. A goal exclusionary negative sampling mechanism tailored for mashup development is also developed to improve training performance. Extensive experiments on a real-world dataset demonstrate the effectiveness of our approach.

8. Sequential Recommendation with Auxiliary Item Relationships via  Multi-Relational Transformer

Ziwei Fan, Zhiwei Liu, Chen Wang, Peijie Huang, Hao Peng, Philip S. Yu

​​https://arxiv.org/abs/2210.13572​​

Sequential Recommendation (SR) models user dynamics and predicts the next preferred items based on the user history. Existing SR methods model the 'was interacted before' item-item transitions observed in sequences, which can be viewed as an item relationship. However, there are multiple auxiliary item relationships, e.g., items from similar brands and with similar contents in real-world scenarios. Auxiliary item relationships describe item-item affinities in multiple different semantics and alleviate the long-lasting cold start problem in the recommendation. However, it remains a significant challenge to model auxiliary item relationships in SR.

9. Coupling User Preference with External Rewards to Enable Driver-centered  and Resource-aware EV Charging Recommendation

Chengyin Li, Zheng Dong, Nathan Fisher, Dongxiao Zhu

​​https://arxiv.org/abs/2210.12693​​

Electric Vehicle (EV) charging recommendation that both accommodates user preference and adapts to the ever-changing external environment arises as a cost-effective strategy to alleviate the range anxiety of private EV drivers. Previous studies focus on centralized strategies to achieve optimized resource allocation, particularly useful for privacy-indifferent taxi fleets and fixed-route public transits. However, private EV driver seeks a more personalized and resource-aware charging recommendation that is tailor-made to accommodate the user preference (when and where to charge) yet sufficiently adaptive to the spatiotemporal mismatch between charging supply and demand. Here we propose a novel Regularized Actor-Critic (RAC) charging recommendation approach that would allow each EV driver to strike an optimal balance between the user preference (historical charging pattern) and the external reward (driving distance and wait time). Experimental results on two real-world datasets demonstrate the unique features and superior performance of our approach to the competing methods.

10. Self-supervised Graph-based Point-of-interest Recommendation

Yang Li, Tong Chen, Peng-Fei Zhang, Zi Huang, Hongzhi Yin

​​https://arxiv.org/abs/2210.12506​​

The exponential growth of Location-based Social Networks (LBSNs) has greatly stimulated the demand for precise location-based recommendation services. Next Point-of-Interest (POI) recommendation, which aims to provide personalised POI suggestions for users based on their visiting histories, has become a prominent component in location-based e-commerce. Recent POI recommenders mainly employ self-attention mechanism or graph neural networks to model complex high-order POI-wise interactions. However, most of them are merely trained on the historical check-in data in a standard supervised learning manner, which fail to fully explore each user's multi-faceted preferences, and suffer from data scarcity and long-tailed POI distribution, resulting in sub-optimal performance. To this end, we propose a Self-s}upervised Graph-enhanced POI Recommender (S2GRec) for next POI recommendation. In particular, we devise a novel Graph-enhanced Self-attentive layer to incorporate the collaborative signals from both global transition graph and local trajectory graphs to uncover the transitional dependencies among POIs and capture a user's temporal interests. In order to counteract the scarcity and incompleteness of POI check-ins, we propose a novel self-supervised learning paradigm in \ssgrec, where the trajectory representations are contrastively learned from two augmented views on geolocations and temporal transitions. Extensive experiments are conducted on three real-world LBSN datasets, demonstrating the effectiveness of our model against state-of-the-art methods.

11. Implementation of Trained Factorization Machine Recommendation System on  Quantum Annealer

Chen-Yu Liu, Hsin-Yu Wang, Pei-Yen Liao, Ching-Jui Lai, Min-Hsiu Hsieh

​​https://arxiv.org/abs/2210.12953​​

Factorization Machine (FM) is the most commonly used model to build a recommendation system since it can incorporate side information to improve performance. However, producing item suggestions for a given user with a trained FM is time-consuming. It requires a run-time of , where is the number of items in the dataset. To address this problem, we propose a quadratic unconstrained binary optimization (QUBO) scheme to combine with FM and apply quantum annealing (QA) computation. Compared to classical methods, this hybrid algorithm provides a faster than quadratic speedup in finding good user suggestions. We then demonstrate the aforementioned computational advantage on current NISQ hardware by experimenting with a real example on a D-Wave annealer.

12. Triplet Losses-based Matrix Factorization for Robust Recommendations

Flavio Giobergia

​​https://arxiv.org/abs/2210.12098​​

Much like other learning-based models, recommender systems can be affected by biases in the training data. While typical evaluation metrics (e.g. hit rate) are not concerned with them, some categories of final users are heavily affected by these biases. In this work, we propose using multiple triplet losses terms to extract meaningful and robust representations of users and items. We empirically evaluate the soundness of such representations through several "bias-aware" evaluation metrics, as well as in terms of stability to changes in the training set and agreement of the predictions variance w.r.t. that of each user.

13. Towards Robust Recommender Systems via Triple Cooperative Defense

Qingyang Wang, Defu Lian, Chenwang Wu, Enhong Chen

​​https://arxiv.org/abs/2210.13762​​

Recommender systems are often susceptible to well-crafted fake profiles, leading to biased recommendations. The wide application of recommender systems makes studying the defense against attack necessary. Among existing defense methods, data-processing-based methods inevitably exclude normal samples, while model-based methods struggle to enjoy both generalization and robustness. Considering the above limitations, we suggest integrating data processing and robust model and propose a general framework, Triple Cooperative Defense (TCD), which cooperates to improve model robustness through the co-training of three models. Specifically, in each round of training, we sequentially use the high-confidence prediction ratings (consistent ratings) of any two models as auxiliary training data for the remaining model, and the three models cooperatively improve recommendation robustness. Notably, TCD adds pseudo label data instead of deleting abnormal data, which avoids the cleaning of normal data, and the cooperative training of the three models is also beneficial to model generalization. Through extensive experiments with five poisoning attacks on three real-world datasets, the results show that the robustness improvement of TCD significantly outperforms baselines. It is worth mentioning that TCD is also beneficial for model generalizations.

14. FedGRec: Federated Graph Recommender System with Lazy Update of Latent  Embeddings

李俊義， 黃恒

https://arxiv.org/abs/2210.13686

推薦系統在工業中被廣泛使用，以改善使用者體驗。盡管取得了巨大的成功，但他們最近因收集私人使用者資料而受到批評。聯邦學習 （FL） 是一種無需直接資料共享即可學習分布式資料的新範例。是以，建議使用聯邦推薦器（FedRec）系統來減輕非分布式推薦系統的隐私問題。但是，FedRec系統與其非分布式系統存在性能差距。主要原因是本地用戶端的使用者-項目互動圖不完整，是以FedRec系統無法很好地利用間接使用者-項目互動。在本文中，我們提出了聯邦圖推薦系統（FedGRec）來緩解這一差距。我們的FedGRec系統可以有效地利用間接的使用者-項目互動。更準确地說，在我們的系統中，使用者和伺服器顯式存儲使用者和項目的潛在嵌入，其中潛在嵌入彙總了間接使用者-項目互動的不同順序，并在本地訓練期間用作缺失互動圖的代理。我們進行了廣泛的實證評估，以驗證使用潛在嵌入作為缺失互動圖的代理的有效性;實驗結果表明，與各種基線相比，我們的系統具有更好的性能。本文的簡短版本以 https://federated-learning.org/fl-neurips-2022/

15. 基于會話的推薦系統圖上的異構資訊交叉

鄭曉林， 吳睿， 韓忠軒， 陳朝超， 陳林迅， 韓冰

https://arxiv.org/abs/2210.12940

推薦系統是基本的資訊過濾技術，用于推薦滿足使用者個性和潛在需求的内容或項目。作為解決使用者識别困難和曆史資訊不可用的關鍵解決方案，基于會話的推薦系統提供僅依靠使用者在目前會話中的行為的推薦服務。然而，大多數現有研究并沒有很好地設計用于對異構使用者行為進行模組化并在實際場景中捕獲它們之間的關系。為了填補這一空白，在本文中，我們提出了一種新的基于圖的方法，即圖上的異構資訊交叉（HICG）。HICG利用會話中的多種使用者行為來建構異構圖，并通過有效地交叉圖上的異構資訊來捕捉使用者目前的興趣和他們的長期偏好。此外，我們還提出了一個名為HICG-CL的增強版本，它結合了對比學習（CL）技術來增強項目表示能力。通過利用不同會話之間的項目共現關系，HICG-CL 提高了 HICG 的推薦性能。我們在三個真實世界的推薦資料集上進行了廣泛的實驗，結果驗證了（i）HICG通過在異構圖上利用多種類型的行為實作了最先進的性能。（ii） HICG-CL通過拟議的對比學習子產品進一步顯著提高了HICG的推薦績效。

16. 學習可轉移順序推薦器的向量量化項表示

侯宇鵬， 何占奎， 朱利安·麥考利， 趙鑫

https://arxiv.org/abs/2210.12316

最近，自然語言文本的通用性已被用于開發可轉移的推薦系統。基本思想是使用預先訓練的語言模型 （PLM） 将項目文本編碼為項目表示形式。盡管具有可轉移性，但項目文本和項目表示之間的綁定可能過于緊密，導緻諸如過分強調文本相似性和誇大域差距等潛在問題。為了解決這個問題，本文提出了VQ-Rec，這是一種學習可轉移順序推薦器的向量量化項目表示的新方法。我們方法的主要新穎之處在于新的項目表示方案：它首先将項目文本映射到離散索引的向量（稱為項目代碼），然後使用這些索引來查找代碼嵌入表以派生項目表示。這樣的方案可以表示為“文本->代碼->表示”。基于這種表示方案，我們進一步提出了一種增強的對比預訓練方法，使用半合成和混合域代碼表示作為硬否定。此外，我們設計了一種基于可微置換網絡的跨域微調方法。在六個公共基準上進行的廣泛實驗證明了所提出的方法在跨領域和跨平台設定中的有效性。

17. 采用推薦系統支援資料和算法共享

彼得·穆爾納、斯特凡·施梅爾達、迪特·泰勒、斯蒂芬妮·林施塔特、多米尼克·科瓦爾德

https://arxiv.org/abs/2210.11828

資料和算法共享是資料和人工智能驅動型經濟的必要組成部分。資料和算法的有效共享依賴于使用者、資料提供者和算法提供者之間的積極互相作用。盡管衆所周知，推薦系統可以有效地将電子商務環境中的使用者和項目互連起來，但缺乏對推薦系統在資料和算法共享方面的适用性的研究。為了填補這一空白，我們确定了六種支援資料和算法共享的推薦場景，其中四種場景與電子商務應用程式中的傳統推薦場景有很大不同。我們使用基于OpenML資料和算法共享平台的互動資料的新型資料集來評估這些推薦場景，我們也為科學界提供了該資料集。具體而言，我們研究了三種類型的推薦方法，即受歡迎程度推薦、協作推薦和基于内容的推薦。我們發現，基于協作的建議在所有方案中都能提供最準确的建議。此外，推薦的準确性在很大程度上取決于特定場景，例如，針對使用者的算法建議比針對資料集的算法建議更困難。最後，基于内容的方法生成了涵蓋最多資料集和算法的流行度偏差最小的建議。