With the development of multimedia systems, multimodal recommendations are playing an essential role, as they can leverage rich contexts beyond interactions. Existing methods mainly regard multimodal information as an auxiliary, using them to help learn ID features; However, there exist semantic gaps among multimodal content features and ID-based features, for which directly using multimodal information as an auxiliary would lead to misalignment in representations of users and items. In this paper, we first systematically investigate the misalignment issue in multimodal recommendations, and propose a solution named AlignRec. In AlignRec, the recommendation objective is decomposed into three alignments, namely alignment within contents, alignment between content and categorical ID, and alignment between users and items. Each alignment is characterized by a specific objective function and is integrated into our multimodal recommendation framework. To effectively train AlignRec, we propose starting from pre-training the first alignment to obtain unified multimodal features and subsequently training the following two alignments together with these features as input. As it is essential to analyze whether each multimodal feature helps in training and accelerate the iteration cycle of recommendation models, we design three new classes of metrics to evaluate intermediate performance. Our extensive experiments on three real-world datasets consistently verify the superiority of AlignRec compared to nine baselines. We also find that the multimodal features generated by AlignRec are better than currently used ones, which are to be open-sourced in our repository https://github.com/sjtulyf123/AlignRec_CIKM24.

The essence of information retrieval (IR) is to find the most useful information items (or documents) according to the user’s information need and present the items to the users in the form of a ranking list. The widely used evaluation metrics for a ranking list are NDCG, MAP, hit ratio etc., which are based on strong assumptions on the users’ examining and click behaviors when interacting with the ranking list. In modern IR scenarios, it has been shown that users’ behavior can be highly personalized, diverse and dynamic, which leads to the failure of those assumptions. Click models (CMs) are proposed to learn such complex user behaviors. However, most of existing works on CM still focus on fitting the logged behavior data while little attention has been paid to how CMs can both evaluate and improve rankers effectively. In this paper, we perform an in-depth investigation into how a CM could simultaneously evaluate and improve the ranking policy for IR. Specifically, we first make a theoretical analysis on the discrepancy of evaluated performance between a learned click model and the real user. Then based on the analysis, we discuss the principles of learning a good CM that could reduce such a discrepancy and accordingly propose a novel rank-oriented click model (RankCM). Furthermore, we conducted extensive experiments on how a CM can both evaluate and improve a ranker effectively based on four tasks, namely data fitting, click simulation, policy ranking and policy improvement, where RankCM demonstrates its comprehensive effectiveness and superiority over the compared CMs. Our study claims that adversarially trained environment models are effective policy evaluators and improvers, and this work could serve as an application to information retrieval. The innovations from the experiments as well as the future promising investigations are further discussed.

Integrated ranking is critical in industrial recommendation systems and has attracted increasing attention. In an integrated ranking system, items from multiple channels are merged together and form an integrated list. During this process, apart from optimizing the system's utility like the total number of clicks, a fair allocation of the exposure opportunities over different channels also needs to be satisfied. To address this problem, we propose an integrated ranking model called Integrated Deep-Q Network (iDQN), which jointly considers user preferences, the platform's utility, and the exposure fairness. Extensive offline experiments validate the effectiveness of iDQN in managing the tradeoff between utility and fairness. Moreover, iDQN also has been deployed onto the online AppStore platform in Huawei, where the online A/B test shows iDQN outperforms the baseline by 1.87% and 2.21% in terms of utility and fairness, respectively.