论文周报 | 推荐系统领域最新研究进展, 含CIKM、ICDM、RecSys等会议论文

本文精选了上周（0904-0910）最新发布的21篇推荐系统相关论文，主要研究方向包括推荐中的向量压缩、推荐中的公平性、大语言模型推荐系统、多场景推荐、跨域推荐、多行为推荐、对话推荐等。

另外，祝各位老师教师节快乐(*^▽^*)！

1. Learning Compact Compositional Embeddings via Regularized Pruning for Recommendation, ICDM 2023

2. Fairness of Exposure in Dynamic Recommendation

3. STGIN: Spatial-Temporal Graph Interaction Network for Large-scale POI Recommendation, CIKM2023

4. Scenario-Aware Hierarchical Dynamic Network for Multi-Scenario Recommendation

5. Distributional Domain-Invariant Preference Matching for Cross-Domain Recommendation, ICDM2023

6. Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems

7. Large Language Models for Generative Recommendation: A Survey and Visionary Discussions

8. Multi-Relational Contrastive Learning for Recommendation, RecSys2023

9. Hessian-aware Quantized Node Embeddings for Recommendation, RecSys2023

10. Zero-Shot Recommendations with Pre-Trained Large Language Models for Multimodal Nudging

11. VideolandGPT: A User Study on a Conversational Recommender System, Workshop@RecSys2023

12. Evaluating ChatGPT as a Recommender System: A Rigorous Approach

13. Behind Recommender Systems: the Geography of the ACM RecSys Community, Workshop@RecSys2023

14. Impression-Informed Multi-Behavior Recommender System: A Hierarchical Graph Attention Approach, Workshop@RecSys2023

15. Tidying Up the Conversational Recommender Systems' Biases, Workshop@RecSys2023

16. MvFS: Multi-view Feature Selection for Recommender System, CIKM2023

17. Robust Recommender System: A Survey and Future Directions

18. Towards Individual and Multistakeholder Fairness in Tourism Recommender Systems

19. In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems, MM2023

20. Content Prompting: Modeling Content Provider Dynamics to Improve User Welfare in Recommender Ecosystems, from Google

21. Concentrating on the Impact: Consequence-based Explanations in Recommender Systems

1. Learning Compact Compositional Embeddings via Regularized Pruning for Recommendation, ICDM 2023

Xurong Liang, Tong Chen, Quoc Viet Hung Nguyen, Jianxin Li, Hongzhi Yin

https://arxiv.org/abs/2309.03518

Latent factor models are the dominant backbones of contemporary recommender systems (RSs) given their performance advantages, where a unique vector embedding with a fixed dimensionality (e.g., 128) is required to represent each entity (commonly a user/item). Due to the large number of users and items on e-commerce sites, the embedding table is arguably the least memory-efficient component of RSs. For any lightweight recommender that aims to efficiently scale with the growing size of users/items or to remain applicable in resource-constrained settings, existing solutions either reduce the number of embeddings needed via hashing, or sparsify the full embedding table to switch off selected embedding dimensions. However, as hash collision arises or embeddings become overly sparse, especially when adapting to a tighter memory budget, those lightweight recommenders inevitably have to compromise their accuracy. To this end, we propose a novel compact embedding framework for RSs, namely Compositional Embedding with Regularized Pruning (CERP). Specifically, CERP represents each entity by combining a pair of embeddings from two independent, substantially smaller meta-embedding tables, which are then jointly pruned via a learnable element-wise threshold. In addition, we innovatively design a regularized pruning mechanism in CERP, such that the two sparsified meta-embedding tables are encouraged to encode information that is mutually complementary. Given the compatibility with agnostic latent factor models, we pair CERP with two popular recommendation models for extensive experiments, where results on two real-world datasets under different memory budgets demonstrate its superiority against state-of-the-art baselines. The codebase of CERP is available in

2. Fairness of Exposure in Dynamic Recommendation

Masoud Mansoury, Bamshad Mobasher

https://arxiv.org/abs/2309.02322

Exposure bias is a well-known issue in recommender systems where the exposure is not fairly distributed among items in the recommendation results. This is especially problematic when bias is amplified over time as a few items (e.g., popular ones) are repeatedly over-represented in recommendation lists and users' interactions with those items will amplify bias towards those items over time resulting in a feedback loop. This issue has been extensively studied in the literature in static recommendation environment where a single round of recommendation result is processed to improve the exposure fairness. However, less work has been done on addressing exposure bias in a dynamic recommendation setting where the system is operating over time, the recommendation model and the input data are dynamically updated with ongoing user feedback on recommended items at each round. In this paper, we study exposure bias in a dynamic recommendation setting. Our goal is to show that existing bias mitigation methods that are designed to operate in a static recommendation setting are unable to satisfy fairness of exposure for items in long run. In particular, we empirically study one of these methods and show that repeatedly applying this method fails to fairly distribute exposure among items in long run. To address this limitation, we show how this method can be adapted to effectively operate in a dynamic recommendation setting and achieve exposure fairness for items in long run. Experiments on a real-world dataset confirm that our solution is superior in achieving long-term exposure fairness for the items while maintaining the recommendation accuracy.

3. STGIN: Spatial-Temporal Graph Interaction Network for Large-scale POI Recommendation, CIKM2023

Shaohua Liu, Yu Qi, Gen Li, Mingjian Chen, Teng Zhang, Jia Cheng, Jun Lei

https://arxiv.org/abs/2309.02251

In Location-Based Services, Point-Of-Interest(POI) recommendation plays a crucial role in both user experience and business opportunities. Graph neural networks have been proven effective in providing personalized POI recommendation services. However, there are still two critical challenges. First, existing graph models attempt to capture users' diversified interests through a unified graph, which limits their ability to express interests in various spatial-temporal contexts. Second, the efficiency limitations of graph construction and graph sampling in large-scale systems make it difficult to adapt quickly to new real-time interests. To tackle the above challenges, we propose a novel Spatial-Temporal Graph Interaction Network. Specifically, we construct subgraphs of spatial, temporal, spatial-temporal, and global views respectively to precisely characterize the user's interests in various contexts. In addition, we design an industry-friendly framework to track the user's latest interests. Extensive experiments on the real-world dataset show that our method outperforms state-of-the-art models. This work has been successfully deployed in a large e-commerce platform, delivering a 1.1% CTR and 6.3% RPM improvement.

4. Scenario-Aware Hierarchical Dynamic Network for Multi-Scenario Recommendation

Jingtong Gao, Bo Chen, Menghui Zhu, Xiangyu Zhao, Xiaopeng Li, Yuhao Wang, Yichao Wang, Huifeng Guo, Ruiming Tang

https://arxiv.org/abs/2309.02061

Click-Through Rate (CTR) prediction is a fundamental technique in recommendation and advertising systems. Recent studies have shown that implementing multi-scenario recommendations contributes to strengthening information sharing and improving overall performance. However, existing multi-scenario models only consider coarse-grained explicit scenario modeling that depends on pre-defined scenario identification from manual prior rules, which is biased and sub-optimal. To address these limitations, we propose a Scenario-Aware Hierarchical Dynamic Network for Multi-Scenario Recommendations (HierRec), which perceives implicit patterns adaptively and conducts explicit and implicit scenario modeling jointly. In particular, HierRec designs a basic scenario-oriented module based on the dynamic weight to capture scenario-specific information. Then the hierarchical explicit and implicit scenario-aware modules are proposed to model hybrid-grained scenario information. The multi-head implicit modeling design contributes to perceiving distinctive patterns from different perspectives. Our experiments on two public datasets and real-world industrial applications on a mainstream online advertising platform demonstrate that our HierRec outperforms existing models significantly.

5. Distributional Domain-Invariant Preference Matching for Cross-Domain Recommendation, ICDM2023

Jing Du, Zesheng Ye, Bin Guo, Zhiwen Yu, Lina Yao

https://arxiv.org/abs/2309.01343

Learning accurate cross-domain preference mappings in the absence of overlapped users/items has presented a persistent challenge in Non-overlapping Cross-domain Recommendation (NOCDR). Despite the efforts made in previous studies to address NOCDR, several limitations still exist. Specifically, 1) while some approaches substitute overlapping users/items with overlapping behaviors, they cannot handle NOCDR scenarios where such auxiliary information is unavailable; 2) often, cross-domain preference mapping is modeled by learning deterministic explicit representation matchings between sampled users in two domains. However, this can be biased due to individual preferences and thus fails to incorporate preference continuity and universality of the general population. In light of this, we assume that despite the scattered nature of user behaviors, there exists a consistent latent preference distribution shared among common people. Modeling such distributions further allows us to capture the continuity in user behaviors within each domain and discover preference invariance across domains. To this end, we propose a Distributional domain-invariant Preference Matching method for non-overlapping Cross-Domain Recommendation (DPMCDR). For each domain, we hierarchically approximate a posterior of domain-level preference distribution with empirical evidence derived from user-item interactions. Next, we aim to build distributional implicit matchings between the domain-level preferences of two domains. This process involves mapping them to a shared latent space and seeking a consensus on domain-invariant preference by minimizing the distance between their distributional representations therein. In this way, we can identify the alignment of two non-overlapping domains if they exhibit similar patterns of domain-invariant preference.

6. Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems

Junting Wang, Adit Krishnan, Hari Sundaram, Yunzhe Li

https://arxiv.org/abs/2309.01188

Modern neural collaborative filtering techniques are critical to the success of e-commerce, social media, and content-sharing platforms. However, despite technical advances -- for every new application domain, we need to train an NCF model from scratch. In contrast, pre-trained vision and language models are routinely applied to diverse applications directly (zero-shot) or with limited fine-tuning. Inspired by the impact of pre-trained models, we explore the possibility of pre-trained recommender models that support building recommender systems in new domains, with minimal or no retraining, without the use of any auxiliary user or item information. Zero-shot recommendation without auxiliary information is challenging because we cannot form associations between users and items across datasets when there are no overlapping users or items. Our fundamental insight is that the statistical characteristics of the user-item interaction matrix are universally available across different domains and datasets. Thus, we use the statistical characteristics of the user-item interaction matrix to identify dataset-independent representations for users and items. We show how to learn universal (i.e., supporting zero-shot adaptation without user or item auxiliary information) representations for nodes and edges from the bipartite user-item interaction graph. We learn representations by exploiting the statistical properties of the interaction data, including user and item marginals, and the size and density distributions of their clusters.

With extensive experiments on five diverse public real-world datasets, we show that the proposed dataset-agnostic features, combined with a pre-trained recommendation model, generalizes to unseen users and unseen items within a dataset and across different datasets (i.e., cross-domain, zero-shot) with comparable performance to state-of-the-art neural recommenders in traditional single-dataset settings. Furthermore, we show for the in-domain setting, the proposed features can boost the performance of existing state-of-the-art neural recommender models by up to 14% on three out of five datasets via a simple post-hoc interpolation on the ranking prediction. Pre-trained models will have a significant application impact on developing recommender systems for new application domains with minimal fine-tuning (few-shot) or no training (zero-shot). Our code and datasets are available for review. https://anonymous.4open.science/r/uni_recsys-2BFE/README.md

7. Large Language Models for Generative Recommendation: A Survey and Visionary Discussions

Lei Li, Yongfeng Zhang, Dugang Liu, Li Chen

https://arxiv.org/abs/2309.01157

Recent years have witnessed the wide adoption of large language models (LLM) in different fields, especially natural language processing and computer vision. Such a trend can also be observed in recommender systems (RS). However, most of related work treat LLM as a component of the conventional recommendation pipeline (e.g., as a feature extractor) which may not be able to fully leverage the generative power of LLM. Instead of separating the recommendation process into multiple stages such as score computation and re-ranking, this process can be simplified to one stage with LLM: directly generating recommendations from the complete pool of items. This survey reviews the progress, methods and future directions of LLM-based generative recommendation by examining three questions: 1) What generative recommendation is, 2) Why RS should advance to generative recommendation, and 3) How to implement LLM-based generative recommendation for various RS tasks. We hope that the survey can provide the context and guidance needed to explore this interesting and emerging topic.

8. Multi-Relational Contrastive Learning for Recommendation, RecSys2023

Wei Wei, Lianghao Xia, Chao Huang

https://arxiv.org/abs/2309.01103

Personalized recommender systems play a crucial role in capturing users' evolving preferences over time to provide accurate and effective recommendations on various online platforms. However, many recommendation models rely on a single type of behavior learning, which limits their ability to represent the complex relationships between users and items in real-life scenarios. In such situations, users interact with items in multiple ways, including clicking, tagging as favorite, reviewing, and purchasing. To address this issue, we propose the Relation-aware Contrastive Learning (RCL) framework, which effectively models dynamic interaction heterogeneity. The RCL model incorporates a multi-relational graph encoder that captures short-term preference heterogeneity while preserving the dedicated relation semantics for different types of user-item interactions. Moreover, we design a dynamic cross-relational memory network that enables the RCL model to capture users' long-term multi-behavior preferences and the underlying evolving cross-type behavior dependencies over time. To obtain robust and informative user representations with both commonality and diversity across multi-behavior interactions, we introduce a multi-relational contrastive learning paradigm with heterogeneous short- and long-term interest modeling. Our extensive experimental studies on several real-world datasets demonstrate the superiority of the RCL recommender system over various state-of-the-art baselines in terms of recommendation accuracy and effectiveness.

9. Hessian-aware Quantized Node Embeddings for Recommendation, RecSys2023

Huiyuan Chen, Kaixiong Zhou, Kwei-Herng Lai, Chin-Chia Michael Yeh, Yan Zheng, Xia Hu, Hao Yang

https://arxiv.org/abs/2309.01032

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in recommender systems. Nevertheless, the process of searching and ranking from a large item corpus usually requires high latency, which limits the widespread deployment of GNNs in industry-scale applications. To address this issue, many methods compress user/item representations into the binary embedding space to reduce space requirements and accelerate inference. Also, they use the Straight-through Estimator (STE) to prevent vanishing gradients during back-propagation. However, the STE often causes the gradient mismatch problem, leading to sub-optimal results.

In this work, we present the Hessian-aware Quantized GNN (HQ-GNN) as an effective solution for discrete representations of users/items that enable fast retrieval. HQ-GNN is composed of two components: a GNN encoder for learning continuous node embeddings and a quantized module for compressing full-precision embeddings into low-bit ones. Consequently, HQ-GNN benefits from both lower memory requirements and faster inference speeds compared to vanilla GNNs. To address the gradient mismatch problem in STE, we further consider the quantized errors and its second-order derivatives for better stability. The experimental results on several large-scale datasets show that HQ-GNN achieves a good balance between latency and performance.

10. Zero-Shot Recommendations with Pre-Trained Large Language Models for Multimodal Nudging

Rachel Harrison, Anton Dereventsov, Anton Bibin

https://arxiv.org/abs/2309.01026

We present a method for zero-shot recommendation of multimodal non-stationary content that leverages recent advancements in the field of generative AI. We propose rendering inputs of different modalities as textual descriptions and to utilize pre-trained LLMs to obtain their numerical representations by computing semantic embeddings. Once unified representations of all content items are obtained, the recommendation can be performed by computing an appropriate similarity metric between them without any additional learning. We demonstrate our approach on a synthetic multimodal nudging environment, where the inputs consist of tabular, textual, and visual data.

11. VideolandGPT: A User Study on a Conversational Recommender System, Workshop@RecSys2023

Mateo Gutierrez Granada, Dina Zilbershtein, Daan Odijk, Francesco Barile

https://arxiv.org/abs/2309.03645

This paper investigates how large language models (LLMs) can enhance recommender systems, with a specific focus on Conversational Recommender Systems that leverage user preferences and personalised candidate selections from existing ranking models. We introduce VideolandGPT, a recommender system for a Video-on-Demand (VOD) platform, Videoland, which uses ChatGPT to select from a predetermined set of contents, considering the additional context indicated by users' interactions with a chat interface. We evaluate ranking metrics, user experience, and fairness of recommendations, comparing a personalised and a non-personalised version of the system, in a between-subject user study. Our results indicate that the personalised version outperforms the non-personalised in terms of accuracy and general user satisfaction, while both versions increase the visibility of items which are not in the top of the recommendation lists. However, both versions present inconsistent behavior in terms of fairness, as the system may generate recommendations which are not available on Videoland.

12. Evaluating ChatGPT as a Recommender System: A Rigorous Approach

Dario Di Palma, Giovanni Maria Biancofiore, Vito Walter Anelli, Fedelucio Narducci, Tommaso Di Noia, Eugenio Di Sciascio

https://arxiv.org/abs/2309.03613

Recent popularity surrounds large AI language models due to their impressive natural language capabilities. They contribute significantly to language-related tasks, including prompt-based learning, making them valuable for various specific tasks. This approach unlocks their full potential, enhancing precision and generalization. Research communities are actively exploring their applications, with ChatGPT receiving recognition. Despite extensive research on large language models, their potential in recommendation scenarios still needs to be explored. This study aims to fill this gap by investigating ChatGPT's capabilities as a zero-shot recommender system. Our goals include evaluating its ability to use user preferences for recommendations, reordering existing recommendation lists, leveraging information from similar users, and handling cold-start situations. We assess ChatGPT's performance through comprehensive experiments using three datasets (MovieLens Small, Lastfm, , and Facebook Book). We compare ChatGPT's performance against standard recommendation algorithms and other large language models, such as GPT-3.5 and PaLM-2. To measure recommendation effectiveness, we employ widely-used evaluation metrics like Mean Average Precision (MAP), Recall, Precision, F1, normalized Discounted Cumulative Gain (nDCG), Item Coverage, Expected Popularity Complement (EPC), Average Coverage of Long Tail (ACLT), Average Recommendation Popularity (ARP), and Popularity-based Ranking-based Equal Opportunity (PopREO). Through thoroughly exploring ChatGPT's abilities in recommender systems, our study aims to contribute to the growing body of research on the versatility and potential applications of large language models. Our experiment code is available on the GitHub repository: https://github.com/sisinflab/Recommender-ChatGPT

13. Behind Recommender Systems: the Geography of the ACM RecSys Community, Workshop@RecSys2023

Lorenzo Porcaro, João Vinagre, Pedro Frau, Isabelle Hupont, Emilia Gómez

https://arxiv.org/abs/2309.03512

The amount and dissemination rate of media content accessible online is nowadays overwhelming. Recommender Systems filter this information into manageable streams or feeds, adapted to our personal needs or preferences. It is of utter importance that algorithms employed to filter information do not distort or cut out important elements from our perspectives of the world. Under this principle, it is essential to involve diverse views and teams from the earliest stages of their design and development. This has been highlighted, for instance, in recent European Union regulations such as the Digital Services Act, via the requirement of risk monitoring, including the risk of discrimination, and the AI Act, through the requirement to involve people with diverse backgrounds in the development of AI systems. We look into the geographic diversity of the recommender systems research community, specifically by analyzing the affiliation countries of the authors who contributed to the ACM Conference on Recommender Systems (RecSys) during the last 15 years. This study has been carried out in the framework of the Diversity in AI - DivinAI project, whose main objective is the long-term monitoring of diversity in AI forums through a set of indexes.

14. Impression-Informed Multi-Behavior Recommender System: A Hierarchical Graph Attention Approach, Workshop@RecSys2023

Dong Li, Divya Bhargavi, Vidya Sagar Ravipati

https://arxiv.org/abs/2309.03169

While recommender systems have significantly benefited from implicit feedback, they have often missed the nuances of multi-behavior interactions between users and items. Historically, these systems either amalgamated all behaviors, such as impression (formerly view), add-to-cart, and buy, under a singular 'interaction' label, or prioritized only the target behavior, often the buy action, discarding valuable auxiliary signals. Although recent advancements tried addressing this simplification, they primarily gravitated towards optimizing the target behavior alone, battling with data scarcity. Additionally, they tended to bypass the nuanced hierarchy intrinsic to behaviors. To bridge these gaps, we introduce the Hierarchical Multi-behavior Graph Attention Network (HMGN). This pioneering framework leverages attention mechanisms to discern information from both inter and intra-behaviors while employing a multi-task Hierarchical Bayesian Personalized Ranking (HBPR) for optimization. Recognizing the need for scalability, our approach integrates a specialized multi-behavior sub-graph sampling technique. Moreover, the adaptability of HMGN allows for the seamless inclusion of knowledge metadata and time-series data. Empirical results attest to our model's prowess, registering a notable performance boost of up to 64% in NDCG@100 metrics over conventional graph neural network methods.

15. Tidying Up the Conversational Recommender Systems' Biases, Workshop@RecSys2023

Armin Moradi, Golnoosh Farnadi

https://arxiv.org/abs/2309.02550

The growing popularity of language models has sparked interest in conversational recommender systems (CRS) within both industry and research circles. However, concerns regarding biases in these systems have emerged. While individual components of CRS have been subject to bias studies, a literature gap remains in understanding specific biases unique to CRS and how these biases may be amplified or reduced when integrated into complex CRS models. In this paper, we provide a concise review of biases in CRS by surveying recent literature. We examine the presence of biases throughout the system's pipeline and consider the challenges that arise from combining multiple models. Our study investigates biases in classic recommender systems and their relevance to CRS. Moreover, we address specific biases in CRS, considering variations with and without natural language understanding capabilities, along with biases related to dialogue systems and language models. Through our findings, we highlight the necessity of adopting a holistic perspective when dealing with biases in complex CRS models.

16. MvFS: Multi-view Feature Selection for Recommender System, CIKM2023

Youngjune Lee, Yeongjong Jeong, Keunchan Park, SeongKu Kang

https://arxiv.org/abs/2309.02064

Feature selection, which is a technique to select key features in recommender systems, has received increasing research attention. Recently, Adaptive Feature Selection (AdaFS) has shown remarkable performance by adaptively selecting features for each data instance, considering that the importance of a given feature field can vary significantly across data. However, this method still has limitations in that its selection process could be easily biased to major features that frequently occur. To address these problems, we propose Multi-view Feature Selection (MvFS), which selects informative features for each instance more effectively. Most importantly, MvFS employs a multi-view network consisting of multiple sub-networks, each of which learns to measure the feature importance of a part of data with different feature patterns. By doing so, MvFS mitigates the bias problem towards dominant patterns and promotes a more balanced feature selection process. Moreover, MvFS adopts an effective importance score modeling strategy which is applied independently to each field without incurring dependency among features. Experimental results on real-world datasets demonstrate the effectiveness of MvFS compared to state-of-the-art baselines.

17. Robust Recommender System: A Survey and Future Directions

Kaike Zhang, Qi Cao, Fei Sun, Yunfan Wu, Shuchang Tao, Huawei Shen, Xueqi Cheng

https://arxiv.org/abs/2309.02057

With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload. However, their practical deployment often encounters "dirty" data, where noise or malicious information can lead to abnormal recommendations. Research on improving recommender systems' robustness against such dirty data has thus gained significant attention. This survey provides a comprehensive review of recent work on recommender systems' robustness. We first present a taxonomy to organize current techniques for withstanding malicious attacks and natural noise. We then explore state-of-the-art methods in each category, including fraudster detection, adversarial training, certifiable robust training against malicious attacks, and regularization, purification, self-supervised learning against natural noise. Additionally, we summarize evaluation metrics and common datasets used to assess robustness. We discuss robustness across varying recommendation scenarios and its interplay with other properties like accuracy, interpretability, privacy, and fairness. Finally, we delve into open issues and future research directions in this emerging field. Our goal is to equip readers with a holistic understanding of robust recommender systems and spotlight pathways for future research and development.

18. Towards Individual and Multistakeholder Fairness in Tourism Recommender Systems

Ashmi Banerjee, Paromita Banik, Wolfgang Wörndl

https://arxiv.org/abs/2309.02052

This position paper summarizes our published review on individual and multistakeholder fairness in Tourism Recommender Systems (TRS). Recently, there has been growing attention to fairness considerations in recommender systems (RS). It has been acknowledged in research that fairness in RS is often closely tied to the presence of multiple stakeholders, such as end users, item providers, and platforms, as it raises concerns for the fair treatment of all parties involved. Hence, fairness in RS is a multi-faceted concept that requires consideration of the perspectives and needs of the different stakeholders to ensure fair outcomes for them. However, there may often be instances where achieving the goals of one stakeholder could conflict with those of another, resulting in trade-offs.

19. In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems, MM2023

Zhongxuan Han, Chaochao Chen, Xiaolin Zheng, Weiming Liu, Jun Wang, Wenjie Cheng, Yuyuan Li

https://arxiv.org/abs/2309.01335

Recommender systems are typically biased toward a small group of users, leading to severe unfairness in recommendation performance, i.e., User-Oriented Fairness (UOF) issue. The existing research on UOF is limited and fails to deal with the root cause of the UOF issue: the learning process between advantaged and disadvantaged users is unfair. To tackle this issue, we propose an In-processing User Constrained Dominant Sets (In-UCDS) framework, which is a general framework that can be applied to any backbone recommendation model to achieve user-oriented fairness. We split In-UCDS into two stages, i.e., the UCDS modeling stage and the in-processing training stage. In the UCDS modeling stage, for each disadvantaged user, we extract a constrained dominant set (a user cluster) containing some advantaged users that are similar to it. In the in-processing training stage, we move the representations of disadvantaged users closer to their corresponding cluster by calculating a fairness loss. By combining the fairness loss with the original backbone model loss, we address the UOF issue and maintain the overall recommendation performance simultaneously. Comprehensive experiments on three real-world datasets demonstrate that In-UCDS outperforms the state-of-the-art methods, leading to a fairer model with better overall recommendation performance.

20. Content Prompting: Modeling Content Provider Dynamics to Improve User Welfare in Recommender Ecosystems, from Google

Siddharth Prasad, Martin Mladenov, Craig Boutilier

https://arxiv.org/abs/2309.00940

Users derive value from a recommender system (RS) only to the extent that it is able to surface content (or items) that meet their needs/preferences. While RSs often have a comprehensive view of user preferences across the entire user base, content providers, by contrast, generally have only a local view of the preferences of users that have interacted with their content. This limits a provider's ability to offer new content to best serve the broader population. In this work, we tackle this information asymmetry with content prompting policies. A content prompt is a hint or suggestion to a provider to make available novel content for which the RS predicts unmet user demand. A prompting policy is a sequence of such prompts that is responsive to the dynamics of a provider's beliefs, skills and incentives. We aim to determine a joint prompting policy that induces a set of providers to make content available that optimizes user social welfare in equilibrium, while respecting the incentives of the providers themselves. Our contributions include: (i) an abstract model of the RS ecosystem, including content provider behaviors, that supports such prompting; (ii) the design and theoretical analysis of sequential prompting policies for individual providers; (iii) a mixed integer programming formulation for optimal joint prompting using path planning in content space; and (iv) simple, proof-of-concept experiments illustrating how such policies improve ecosystem health and user welfare.

21. Concentrating on the Impact: Consequence-based Explanations in Recommender Systems

Sebastian Lubos, Thi Ngoc Trang Tran, Seda Polat Erdeniz, Merfat El Mansi, Alexander Felfernig, Manfred Wundara, Gerhard Leitner

https://arxiv.org/abs/2308.16708

Recommender systems assist users in decision-making, where the presentation of recommended items and their explanations are critical factors for enhancing the overall user experience. Although various methods for generating explanations have been proposed, there is still room for improvement, particularly for users who lack expertise in a specific item domain. In this study, we introduce the novel concept of consequence-based explanations, a type of explanation that emphasizes the individual impact of consuming a recommended item on the user, which makes the effect of following recommendations clearer. We conducted an online user study to examine our assumption about the appreciation of consequence-based explanations and their impacts on different explanation aims in recommender systems. Our findings highlight the importance of consequence-based explanations, which were well-received by users and effectively improved user satisfaction in recommender systems. These results provide valuable insights for designing engaging explanations that can enhance the overall user experience in decision-making.