论文分享 | 推荐系统相关研究进展

我们从2024-11-21到2024-12-02的25篇文章中精选出5篇优秀的工作分享给读者。

1. Towards Robust Cross-Domain Recommendation with Joint Identifiability of User Preference
2. Recommender Systems for Good (RS4Good): Survey of Use Cases and a Call to Action for Research that Matters
3. OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation
4. Counterfactual Learning-Driven Representation Disentanglement for Search-Enhanced Recommendation
5. Branches, Assemble! Multi-Branch Cooperation Network for Large-Scale Click-Through Rate Prediction at Taobao

1.Towards Robust Cross-Domain Recommendation with Joint Identifiability of User Preference

Authors:Jing Du, Zesheng Ye, Bin Guo, Zhiwen Yu, Jia Wu, Jian Yang, Michael Sheng, Lina Yao

https://arxiv.org/abs/2411.17361

论文摘要

Recent cross-domain recommendation (CDR) stud ies assume that disentangled domain-shared and domain-specific user representations can mitigate domain gaps and facilitate effective knowledge transfer. However, achieving perfect disen tanglement is challenging in practice, because user behaviors in CDR are highly complex, and the true underlying user preferences cannot be fully captured through observed user item interactions alone. Given this impracticability, we instead propose to model joint identifiability that establishes unique correspondence of user representations across domains, ensuring consistent preference modeling even when user behaviors exhibit shifts in different domains. To achieve this, we introduce a hier archical user preference modeling framework that organizes user representations by the neural network encoder’s depth, allowing separate treatment of shallow and deeper subspaces. In the shallow subspace, our framework models the interest centroids for each user within each domain, probabilistically determining the users’ interest belongings and selectively aligning these centroids across domains to ensure fine-grained consistency in domain-irrelevant features. For deeper subspace representations, we enforce joint identifiability by decomposing it into a shared cross-domain stable component and domain-variant components, linked by a bijective transformation for unique correspondence. Empirical studies on real-world CDR tasks with varying domain correlations demonstrate that our method consistently surpasses state-of-the-art, even with weakly correlated tasks, highlighting the importance of joint identifiability in achieving robust CDR.

论文简评

这篇论文提出了一种新的框架——CIDER，用于解决跨域推荐（Cross-Domain Recommendation, CDR）中的用户偏好建模问题。该方法旨在通过组织用户的表示来实现对用户偏好的联合识别，而不是追求完美地解构用户特征。CIDER提出的概念为“联合可辨识性”，这不仅加深了我们对不同领域用户偏好的理解，也使得模型能够以更精细的方式进行近似预测，甚至在两个领域的用户行为存在显著差异时也能取得良好的效果。实验结果表明，相比于现有的竞争方法，在各种交叉领域推荐任务中，CIDER都能表现出显著的优势。

综上所述，本文提出了一个新颖而有效的跨域推荐方法，其主要贡献在于引入了联合可辨识性的概念，并在实践中取得了良好的效果。这些发现对于提升未来跨域推荐系统的性能具有重要的意义。

2.Recommender Systems for Good (RS4Good): Survey of Use Cases and a Call to Action for Research that Matters

Authors:Dietmar Jannach, Alan Said, Marko Tkalčič, Markus Zanker

https://arxiv.org/abs/2411.16645

论文摘要

In the area of recommender systems, the vast majority of research efforts is spent on developing increasingly sophisticated recommendation models, also using increasingly more computational resources. Unfortunately, most of these research efforts target a very small set of application domains, mostly e-commerce and media recommendation. Furthermore, many of these models are never evaluated with users, let alone put into practice. The scientific, economic and societal value of much of these efforts by scholars therefore remains largely unclear. To achieve a stronger positive impact resulting from these efforts, we posit that we as a research community should more often address use cases where recommender systems contribute to societal good (RS4Good). In this opinion piece, we first discuss a number of examples where the use of recommender systems for problems of societal concern has been successfully explored in the literature. We then proceed by outlining a paradigmatic shift that is needed to conduct successful RS4Good research, where the key ingredients are interdisciplinary collaborations and longitudinal evaluation approaches with humans in the loop.

论文简评

这篇论文为当前推荐系统研究领域提出了一个新的视角：关注社会价值（RS4Good）的研究方向。作者认为，尽管推荐系统在电商和媒体等领域发挥了重要作用，但它们的应用范围过于狭窄，未能充分考虑社会层面的实际问题。因此，本文提出了一种新的研究方法，强调通过跨学科合作和长期评估来开发能够解决实际社会问题的推荐系统。这种研究策略不仅有助于推动推荐系统的创新与发展，还有望引领未来的研究方向。总的来说，这篇文章对推荐系统领域的现状进行了深入分析，并提出了建设性的建议，为推动这一领域的发展做出了积极贡献。

3.OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation

Authors:Se-eun Yoon, Xiaokai Wei, Yexi Jiang, Rachit Pareek, Frank Ong, Kevin Gao, Julian McAuley, Michelle Gong

https://arxiv.org/abs/2411.19352

论文摘要

In this paper, we present a systematic effort to design, evaluate, and implement a realistic conversational recommender system (CRS). The objective of our system is to allow users to input free-form text to request recommendations and then receive a list of relevant and diverse items. While previous work on synthetic queries augments large language models (LLMs) with 1-3 tools, we argue that a more extensive toolbox is necessary to effectively handle real user requests. As such, we propose a novel approach that equips LLMs with over 10 tools, providing them access to the internal knowledge base and API calls used in production. We evaluate our model on a dataset of real users and show that it generates relevant, novel, and diverse recommendations compared to vanilla LLMs. Furthermore, we conduct ablation studies to demonstrate the effectiveness of using the full range of tools in our toolbox. We share our designs and lessons learned from deploying the system for an internal alpha release. Our contribution addresses all four key aspects of a practicable CRS: (1) real user requests, (2) augmenting LLMs with a wide variety of tools, (3) extensive evaluation, and (4) deployment insights.

论文简评

OMulet是一个融合了多个工具与大型语言模型以更好地处理真实用户请求的对话推荐系统框架。它强调使用多样化的工具以有效生成推荐，通过对真实用户查询数据集的广泛评估展示了这一点。该框架详细且包含部署见解，这些见解对于实践者将非常有帮助。综上所述，OMulet为解决对话推荐系统中面临的挑战提供了有价值的解决方案，并通过实证研究验证了其有效性。

4.Counterfactual Learning-Driven Representation Disentanglement for Search-Enhanced Recommendation

Authors:Jiajun Cui, Xu Chen, Shuai Xiao, Chen Ju, Jinsong Lan, Qingwen Liu, Wei Zhang

https://arxiv.org/abs/2411.18631

论文摘要

For recommender systems in internet platforms, search activities provide additional insights into user interest through query-click  interactions with items, and are thus widely used for enhancing personalized recommendation. However, these interacted items not only have transferable features matching users’ interest helpful for the recommendation domain, but also have features related to users’ unique intents in the search domain. Such domaingapofitem features is neglected by most current search-enhanced recommen dation methods. They directly incorporate these search behaviors into recommendation, and thus introduce partial negative trans fer. Tackling this problem is challenging due to the lack of explicit supervision signals to disentangle search interactions’ different features matching search-specific intent or general interest. To ad dress this, we propose ClardRec, a Counterfactual learning-driven representation disentanglement framework for search-enhanced recommendation, based on the common belief that a user would click an item under a query not solely because of the item-query matchbutalsoduetotheitem’squery-independentgeneralfeatures (e.g., color or style) that interest the user. These general features ex clude the reflection of search-specific intents contained in queries, ensuring a pure match to users’ underlying interest to complement recommendation. According to counterfactual thinking, how would user preferences and query match change for items if we removed their query-related features in search, we leverage search queries to construct counterfactual signals to disentangle item represen tations, isolating only query-independent general features. These representations subsequently enable feature augmentation and data augmentation for the recommendationscenario. Comprehensive ex periments on real datasets demonstrate ClardRec is effective in both collaborative filtering and sequential recommendation scenarios.

论文简评

ClardRec是针对搜索增强推荐系统中负转移问题提出的一种新型框架。该文通过实验验证了其在现实数据集上的表现优于传统方法，并且提出了一个新颖的方法来分离物品特征与搜索特定意图。此外，文中还发现搜索特定意图与一般兴趣之间存在明显的差异，这为提出的新框架提供了理论基础。这一系列研究不仅解决了当前推荐系统中的负转移问题，而且对提升推荐系统的性能具有重要意义。因此，该文提出的解决方案在实际应用中的推荐系统问题上具有重要价值。

5.Branches, Assemble! Multi-Branch Cooperation Network for Large-Scale Click-Through Rate Prediction at Taobao

Authors:Xu Chen, Zida Cheng, Yuangang Pan, Shuai Xiao, Xiaoming Liu, Jinsong Lan, Qingwen Liu, Ivor W. Tsang

https://arxiv.org/abs/2411.13057

论文摘要

Existing click-through rate (CTR) prediction works have studied the role of feature interaction through a variety of techniques. Each interaction technique exhibits its own strength, and solely using one type could constrain the model’s capability to capture the com plex feature relationships, especially for industrial large-scale data with enormous users and items. Recent research shows that effec tive CTR models often combine an MLP network with a dedicated feature interaction network in a two-parallel structure. However, the interplay and cooperative dynamics between different streams or branches remain under-researched. In this work, we introduce a novel Multi-Branch Cooperation Network (MBCnet) which en ables multiple branch networks to collaborate with each other for better complex feature interaction modeling. Specifically, MBCnet consists of three branches: the Expert-based Feature Grouping and Crossing (EFGC) branch that promotes the model’s memorization ability of specific feature fields, the low rank Cross Net branch and Deep branch to enhance both explicit and implicit feature crossing for improved generalization. Among branches, a novel cooperation scheme is proposed based on two principles: branch co-teaching and moderate differentiation. Branch co-teaching encourages well-learned branches to support poorly-learned ones on specific training samples. Moderate differentiation advocates branches to maintain a reasonable level of difference in their feature representa tions. The cooperation strategy improves learning through mutual knowledge sharing via co-teaching and boosts the discovery of diverse feature interactions across branches. Extensive experiments on large-scale industrial datasets and online A/B test at Taobao app demonstrate MBCnet’s superior performance, delivering a 0.09 point increase in CTR, 1.49% growth in deals, and 1.62% rise in GMV. Core codes will be released soon.

论文简评

我们欢迎您在评论区中留下宝贵的建议！包括但不限于：

• 可以提出推文中论文简评的不足！
• 可以分享最近更值得推荐的论文并给出理由！

推荐阅读