论文周报 | 推荐系统领域最新研究进展，含SIGIR、WWW等顶会论文

地球不爆炸，我们不放假[Doge].

本文精选了上周（0424-0430）最新发布的15篇推荐系统相关论文，主要研究领域为序列推荐和点击率预估，所利用的技术包括自监督学习、多模态学习、预训练技术、扩散模型、概率逻辑推理等。

以下整理了论文标题以及摘要，如感兴趣可移步原文精读。

1. Prediction then Correction: An Abductive Prediction Correction Method for Sequential Recommendation

2. Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation

3. Self-Supervised Multi-Modal Sequential Recommendation

4. PUNR: Pre-training with User Behavior Modeling for News Recommendation

5. ExCalibR: Expected Calibration of Recommendations

6. Attention-guided Multi-step Fusion: A Hierarchical Fusion Network for Multimodal Recommendation

7. LogicRec: Recommendation with Users' Logical Requirements, SIGIR2023

8. Triple Structural Information Modelling for Accurate, Explainable and Interactive Recommendation, SIGIR2023

9. Conditional Denoising Diffusion for Sequential Recommendation

10. Sequential Recommendation with Probabilistic Logical Reasoning

11. Can Perturbations Help Reduce Investment Risks? Risk-Aware Stock Recommendation via Split Variational Adversarial Training

12. Towards Explainable Collaborative Filtering with Taste Clusters Learning, WWW2023

13. COUPA: An Industrial Recommender System for Online to Offline Service Platforms, SIGIR2023

14. E Pluribus Unum: Guidelines on Multi-Objective Evaluation of Recommender Systems

15. EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction, SIGIR2023

1. Prediction then Correction: An Abductive Prediction Correction Method for Sequential Recommendation

Yulong Huang, Yang Zhang, Qifan Wang, Chenxu Wang, Fuli Feng

https://arxiv.org/abs/2304.14050

Sequential recommender models typically generate predictions in a single step during testing, without considering additional prediction correction to enhance performance as humans would. To improve the accuracy of these models, some researchers have attempted to simulate human analogical reasoning to correct predictions for testing data by drawing analogies with the prediction errors of similar training data. However, there are inherent gaps between testing and training data, which can make this approach unreliable. To address this issue, we propose an Abductive Prediction Correction (APC) framework for sequential recommendation. Our approach simulates abductive reasoning to correct predictions. Specifically, we design an abductive reasoning task that infers the most probable historical interactions from the future interactions predicted by a recommender, and minimizes the discrepancy between the inferred and true historical interactions to adjust the predictions.We perform the abductive inference and adjustment using a reversed sequential model in the forward and backward propagation manner of neural networks. Our APC framework is applicable to various differentiable sequential recommender models. We implement it on three backbone models and demonstrate its effectiveness. We release the code at: https://github.com/zyang1580/APC

2. Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation

Yang Zhang, Tianhao Shi, Fuli Feng, Wenjie Wang, Dingxian Wang, Xiangnan He, Yongdong Zhang

https://arxiv.org/abs/2304.13643

Click-Through Rate (CTR) prediction plays a core role in recommender systems, serving as the final-stage filter to rank items for a user. The key to addressing the CTR task is learning feature interactions that are useful for prediction, which is typically achieved by fitting historical click data with the Empirical Risk Minimization (ERM) paradigm. Representative methods include Factorization Machines and Deep Interest Network, which have achieved wide success in industrial applications. However, such a manner inevitably learns unstable feature interactions, i.e., the ones that exhibit strong correlations in historical data but generalize poorly for future serving. In this work, we reformulate the CTR task -- instead of pursuing ERM on historical data, we split the historical data chronologically into several periods (a.k.a, environments), aiming to learn feature interactions that are stable across periods. Such feature interactions are supposed to generalize better to predict future behavior data. Nevertheless, a technical challenge is that existing invariant learning solutions like Invariant Risk Minimization are not applicable, since the click data entangles both environment-invariant and environment-specific correlations. To address this dilemma, we propose Disentangled Invariant Learning (DIL) which disentangles feature embeddings to capture the two types of correlations separately. To improve the modeling efficiency, we further design LightDIL which performs the disentanglement at the higher level of the feature field. Extensive experiments demonstrate the effectiveness of DIL in learning stable feature interactions for CTR. We release the code at: https://github.com/zyang1580/DIL

3. Self-Supervised Multi-Modal Sequential Recommendation

Kunzhe Song, Qingfeng Sun, Can Xu, Kai Zheng, Yaming Yang

https://arxiv.org/abs/2304.13277

With the increasing development of e-commerce and online services, personalized recommendation systems have become crucial for enhancing user satisfaction and driving business revenue. Traditional sequential recommendation methods that rely on explicit item IDs encounter challenges in handling item cold start and domain transfer problems. Recent approaches have attempted to use modal features associated with items as a replacement for item IDs, enabling the transfer of learned knowledge across different datasets. However, these methods typically calculate the correlation between the model's output and item embeddings, which may suffer from inconsistencies between high-level feature vectors and low-level feature embeddings, thereby hindering further model learning. To address this issue, we propose a dual-tower retrieval architecture for sequence recommendation. In this architecture, the predicted embedding from the user encoder is used to retrieve the generated embedding from the item encoder, thereby alleviating the issue of inconsistent feature levels. Moreover, in order to further improve the retrieval performance of the model, we also propose a self-supervised multi-modal pretraining method inspired by the consistency property of contrastive learning. This pretraining method enables the model to align various feature combinations of items, thereby effectively generalizing to diverse datasets with different item features. We evaluate the proposed method on five publicly available datasets and conduct extensive experiments. The results demonstrate significant performance improvement of our method.

4. PUNR: Pre-training with User Behavior Modeling for News Recommendation

Guangyuan Ma, Hongtao Liu, Xing Wu, Wanhui Qian, Zhepeng Lv, Qing Yang, Songlin Hu

https://arxiv.org/abs/2304.12633

News recommendation aims to predict click behaviors based on user behaviors. How to effectively model the user representations is the key to recommending preferred news. Existing works are mostly focused on improvements in the supervised fine-tuning stage. However, there is still a lack of PLM-based unsupervised pre-training methods optimized for user representations. In this work, we propose an unsupervised pre-training paradigm with two tasks, i.e. user behavior masking and user behavior generation, both towards effective user behavior modeling. Firstly, we introduce the user behavior masking pre-training task to recover the masked user behaviors based on their contextual behaviors. In this way, the model could capture a much stronger and more comprehensive user news reading pattern. Besides, we incorporate a novel auxiliary user behavior generation pre-training task to enhance the user representation vector derived from the user encoder. We use the above pre-trained user modeling encoder to obtain news and user representations in downstream fine-tuning. Evaluations on the real-world news benchmark show significant performance improvements over existing baselines.

5. ExCalibR: Expected Calibration of Recommendations

Pannagadatta Shivaswamy

https://arxiv.org/abs/2304.12311

In many recommender systems and search problems, presenting a well balanced set of results can be an important goal in addition to serving highly relevant content. For example, in a movie recommendation system, it may be helpful to achieve a certain balance of different genres, likewise, it may be important to balance between highly popular versus highly personalized shows. Such balances could be thought across many categories and may be required for enhanced user experience, business considerations, fairness objectives etc. In this paper, we consider the problem of calibrating with respect to any given categories over items. We propose a way to balance a trade-off between relevance and calibration via a Linear Programming optimization problem where we learn a doubly stochastic matrix to achieve optimal balance in expectation. We then realize the learned policy using the Birkhoff-von Neumann decomposition of a doubly stochastic matrix. Several optimizations are considered over the proposed basic approach to make it fast. The experiments show that the proposed formulation can achieve a much better trade-off compared to many other baselines. This paper does not prescribe the exact categories to calibrate over (such as genres) universally for applications. This is likely dependent on the particular task or business objective. The main contribution of the paper is that it proposes a framework that can be applied to a variety of problems and demonstrates the efficacy of the proposed method using a few use-cases.

6. Attention-guided Multi-step Fusion: A Hierarchical Fusion Network for Multimodal Recommendation

Yan Zhou, Jie Guo, Hao Sun, Bin Song, Fei Richard Yu

https://arxiv.org/abs/2304.11979

The main idea of multimodal recommendation is the rational utilization of the item's multimodal information to improve the recommendation performance. Previous works directly integrate item multimodal features with item ID embeddings, ignoring the inherent semantic relations contained in the multimodal features. In this paper, we propose a novel and effective aTtention-guided Multi-step FUsion Network for multimodal recommendation, named TMFUN. Specifically, our model first constructs modality feature graph and item feature graph to model the latent item-item semantic structures. Then, we use the attention module to identify inherent connections between user-item interaction data and multimodal data, evaluate the impact of multimodal data on different interactions, and achieve early-step fusion of item features. Furthermore, our model optimizes item representation through the attention-guided multi-step fusion strategy and contrastive learning to improve recommendation performance. The extensive experiments on three real-world datasets show that our model has superior performance compared to the state-of-the-art models.

7. LogicRec: Recommendation with Users' Logical Requirements, SIGIR2023

Zhenwei Tang, Griffin Floto, Armin Toroghi, Shichao Pei, Xiangliang Zhang, Scott Sanner

https://arxiv.org/abs/2304.11722

Users may demand recommendations with highly personalized requirements involving logical operations, e.g., the intersection of two requirements, where such requirements naturally form structured logical queries on knowledge graphs (KGs). To date, existing recommender systems lack the capability to tackle users' complex logical requirements. In this work, we formulate the problem of recommendation with users' logical requirements (LogicRec) and construct benchmark datasets for LogicRec. Furthermore, we propose an initial solution for LogicRec based on logical requirement retrieval and user preference retrieval, where we face two challenges. First, KGs are incomplete in nature. Therefore, there are always missing true facts, which entails that the answers to logical requirements can not be completely found in KGs. In this case, item selection based on the answers to logical queries is not applicable. We thus resort to logical query embedding (LQE) to jointly infer missing facts and retrieve items based on logical requirements. Second, answer sets are under-exploited. Existing LQE methods can only deal with query-answer pairs, where queries in our case are the intersected user preferences and logical requirements. However, the logical requirements and user preferences have different answer sets, offering us richer knowledge about the requirements and preferences by providing requirement-item and preference-item pairs. Thus, we design a multi-task knowledge-sharing mechanism to exploit these answer sets collectively. Extensive experimental results demonstrate the significance of the LogicRec task and the effectiveness of our proposed method.

8. Triple Structural Information Modelling for Accurate, Explainable and Interactive Recommendation, SIGIR2023

Jiahao Liu, Dongsheng Li, Hansu Gu, Tun Lu, Peng Zhang, Li Shang, Ning Gu

https://arxiv.org/abs/2304.11528

In dynamic interaction graphs, user-item interactions usually follow heterogeneous patterns, represented by different structural information, such as user-item co-occurrence, sequential information of user interactions and the transition probabilities of item pairs. However, the existing methods cannot simultaneously leverage all three structural information, resulting in suboptimal performance. To this end, we propose TriSIM4Rec, a triple structural information modeling method for accurate, explainable and interactive recommendation on dynamic interaction graphs. Specifically, TriSIM4Rec consists of 1) a dynamic ideal low-pass graph filter to dynamically mine co-occurrence information in user-item interactions, which is implemented by incremental singular value decomposition (SVD); 2) a parameter-free attention module to capture sequential information of user interactions effectively and efficiently; and 3) an item transition matrix to store the transition probabilities of item pairs. Then, we fuse the predictions from the triple structural information sources to obtain the final recommendation results. By analyzing the relationship between the SVD-based and the recently emerging graph signal processing (GSP)-based collaborative filtering methods, we find that the essence of SVD is an ideal low-pass graph filter, so that the interest vector space in TriSIM4Rec can be extended to achieve explainable and interactive recommendation, making it possible for users to actively break through the information cocoons. Experiments on six public datasets demonstrated the effectiveness of TriSIM4Rec in accuracy, explainability and interactivity.

9. Conditional Denoising Diffusion for Sequential Recommendation

Yu Wang, Zhiwei Liu, Liangwei Yang, Philip S. Yu

https://arxiv.org/abs/2304.11433

Generative models have attracted significant interest due to their ability to handle uncertainty by learning the inherent data distributions. However, two prominent generative models, namely Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs), exhibit challenges that impede achieving optimal performance in sequential recommendation tasks. Specifically, GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. The sparse and noisy nature of sequential recommendation further exacerbates these issues. In response to these limitations, we present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser. This approach streamlines the optimization and generation process by dividing it into easier and tractable steps in a conditional autoregressive manner. Furthermore, we introduce a novel optimization schema that incorporates both cross-divergence loss and contrastive loss. This novel training schema enables the model to generate high-quality sequence/item representations and meanwhile precluding collapse. We conducted comprehensive experiments on four benchmark datasets, and the superior performance achieved by our model attests to its efficacy.

10. Sequential Recommendation with Probabilistic Logical Reasoning

Huanhuan Yuan, Pengpeng Zhao, Xuefeng Xian, Guanfeng Liu, Yanchi Liu, Victor S. Sheng, Lei Zhao

https://arxiv.org/abs/2304.11383

Deep learning and symbolic learning are two frequently employed methods in Sequential Recommendation (SR). Recent neural-symbolic SR models demonstrate their potential to enable SR to be equipped with concurrent perception and cognition capacities. However, neural-symbolic SR remains a challenging problem due to open issues like representing users and items in logical reasoning. In this paper, we combine the Deep Neural Network (DNN) SR models with logical reasoning and propose a general framework named Sequential Recommendation with Probabilistic Logical Reasoning (short for SR-PLR). This framework allows SR-PLR to benefit from both similarity matching and logical reasoning by disentangling feature embedding and logic embedding in the DNN and probabilistic logic network. To better capture the uncertainty and evolution of user tastes, SR-PLR embeds users and items with a probabilistic method and conducts probabilistic logical reasoning on users' interaction patterns. Then the feature and logic representations learned from the DNN and logic network are concatenated to make the prediction. Finally, experiments on various sequential recommendation models demonstrate the effectiveness of the SR-PLR.

11. Can Perturbations Help Reduce Investment Risks? Risk-Aware Stock Recommendation via Split Variational Adversarial Training

Jiezhu Cheng, Kaizhu Huang, Zibin Zheng

https://arxiv.org/abs/2304.11043

In the stock market, a successful investment requires a good balance between profits and risks. Recently, stock recommendation has been widely studied in quantitative investment to select stocks with higher return ratios for investors. Despite the success in making profits, most existing recommendation approaches are still weak in risk control, which may lead to intolerable paper losses in practical stock investing. To effectively reduce risks, we draw inspiration from adversarial perturbations and propose a novel Split Variational Adversarial Training (SVAT) framework for risk-aware stock recommendation. Essentially, SVAT encourages the model to be sensitive to adversarial perturbations of risky stock examples and enhances the model's risk awareness by learning from perturbations. To generate representative adversarial examples as risk indicators, we devise a variational perturbation generator to model diverse risk factors. Particularly, the variational architecture enables our method to provide a rough risk quantification for investors, showing an additional advantage of interpretability. Experiments on three real-world stock market datasets show that SVAT effectively reduces the volatility of the stock recommendation model and outperforms state-of-the-art baseline methods by more than 30% in terms of risk-adjusted profits.

12. Towards Explainable Collaborative Filtering with Taste Clusters Learning, WWW2023

Yuntao Du, Jianxun Lian, Jing Yao, Xiting Wang, Mingqi Wu, Lu Chen, Yunjun Gao, Xing Xie

https://arxiv.org/abs/2304.13937

Collaborative Filtering (CF) is a widely used and effective technique for recommender systems. In recent decades, there have been significant advancements in latent embedding-based CF methods for improved accuracy, such as matrix factorization, neural collaborative filtering, and LightGCN. However, the explainability of these models has not been fully explored. Adding explainability to recommendation models can not only increase trust in the decisionmaking process, but also have multiple benefits such as providing persuasive explanations for item recommendations, creating explicit profiles for users and items, and assisting item producers in design improvements.

In this paper, we propose a neat and effective Explainable Collaborative Filtering (ECF) model that leverages interpretable cluster learning to achieve the two most demanding objectives: (1) Precise - the model should not compromise accuracy in the pursuit of explainability; and (2) Self-explainable - the model's explanations should truly reflect its decision-making process, not generated from post-hoc methods. The core of ECF is mining taste clusters from user-item interactions and item profiles.We map each user and item to a sparse set of taste clusters, and taste clusters are distinguished by a few representative tags. The user-item preference, users/items' cluster affiliations, and the generation of taste clusters are jointly optimized in an end-to-end manner. Additionally, we introduce a forest mechanism to ensure the model's accuracy, explainability, and diversity. To comprehensively evaluate the explainability quality of taste clusters, we design several quantitative metrics, including in-cluster item coverage, tag utilization, silhouette, and informativeness. Our model's effectiveness is demonstrated through extensive experiments on three real-world datasets.

13. COUPA: An Industrial Recommender System for Online to Offline Service Platforms, SIGIR2023

Sicong Xie, Binbin Hu, Fengze Li, Ziqi Liu, Zhiqiang Zhang, Wenliang Zhong, Jun Zhou

https://arxiv.org/abs/2304.12549

Aiming at helping users locally discovery retail services (e.g., entertainment and dinning), Online to Offline (O2O) service platforms have become popular in recent years, which greatly challenge current recommender systems. With the real data in Alipay, a feeds-like scenario for O2O services, we find that recurrence based temporal patterns and position biases commonly exist in our scenarios, which seriously threaten the recommendation effectiveness. To this end, we propose COUPA, an industrial system targeting for characterizing user preference with following two considerations: (1) Time aware preference: we employ the continuous time aware point process equipped with an attention mechanism to fully capture temporal patterns for recommendation. (2) Position aware preference: a position selector component equipped with a position personalization module is elaborately designed to mitigate position bias in a personalized manner. Finally, we carefully implement and deploy COUPA on Alipay with a cooperation of edge, streaming and batch computing, as well as a two-stage online serving mode, to support several popular recommendation scenarios. We conduct extensive experiments to demonstrate that COUPA consistently achieves superior performance and has potential to provide intuitive evidences for recommendation

14. E Pluribus Unum: Guidelines on Multi-Objective Evaluation of Recommender Systems

Patrick John Chia, Giuseppe Attanasio, Jacopo Tagliabue, Federico Bianchi, Ciro Greco, Gabriel de Souza P. Moreira, Davide Eynard, Fahd Husain

https://arxiv.org/abs/2304.10621

Recommender Systems today are still mostly evaluated in terms of accuracy, with other aspects beyond the immediate relevance of recommendations, such as diversity, long-term user retention and fairness, often taking a back seat. Moreover, reconciling multiple performance perspectives is by definition indeterminate, presenting a stumbling block to those in the pursuit of rounded evaluation of Recommender Systems. EvalRS 2022 -- a data challenge designed around Multi-Objective Evaluation -- was a first practical endeavour, providing many insights into the requirements and challenges of balancing multiple objectives in evaluation. In this work, we reflect on EvalRS 2022 and expound upon crucial learnings to formulate a first-principles approach toward Multi-Objective model selection, and outline a set of guidelines for carrying out a Multi-Objective Evaluation challenge, with potential applicability to the problem of rounded evaluation of competing models in real-world deployments.

15. EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction, SIGIR23

Zhen Tian, Ting Bai, Wayne Xin Zhao, Ji-Rong Wen, Zhao Cao

https://arxiv.org/abs/2304.10711

Learning effective high-order feature interactions is very crucial in the CTR prediction task. However, it is very time-consuming to calculate high-order feature interactions with massive features in online e-commerce platforms. Most existing methods manually design a maximal order and further filter out the useless interactions from them. Although they reduce the high computational costs caused by the exponential growth of high-order feature combinations, they still suffer from the degradation of model capability due to the suboptimal learning of the restricted feature orders. The solution to maintain the model capability and meanwhile keep it efficient is a technical challenge, which has not been adequately addressed. To address this issue, we propose an adaptive feature interaction learning model, named as EulerNet, in which the feature interactions are learned in a complex vector space by conducting space mapping according to Euler's formula. EulerNet converts the exponential powers of feature interactions into simple linear combinations of the modulus and phase of the complex features, making it possible to adaptively learn the high-order feature interactions in an efficient way. Furthermore, EulerNet incorporates the implicit and explicit feature interactions into a unified architecture, which achieves the mutual enhancement and largely boosts the model capabilities. Such a network can be fully learned from data, with no need of pre-designed form or order for feature interactions. Extensive experiments conducted on three public datasets have demonstrated the effectiveness and efficiency of our approach. Our code is available at: https://github.com/RUCAIBox/EulerNet