Large foundational models, through upstream pre-training and downstream fine-tuning, have achieved immense success in the broad AI community due to improved model performance and significant reductions in repetitive engineering. By contrast, the transferable one-for-all models in the recommender system field, referred to as TransRec, have made limited progress. The development of TransRec has encountered multiple challenges, among which the lack of large-scale, high-quality transfer learning recommendation dataset and benchmark suites is one of the biggest obstacles. To this end, we introduce NineRec, a TransRec dataset suite that comprises a large-scale source domain recommendation dataset and nine diverse target domain recommendation datasets. Each item in NineRec is accompanied by a descriptive text and a high-resolution cover image. Leveraging NineRec, we enable the implementation of TransRec models by learning from raw multimodal features instead of relying solely on pre-extracted off-the-shelf features. Finally, we present robust TransRec benchmark results with several classical network architectures, providing valuable insights into the field.

The advent of large language models has inspired active and promising research focused on developing text content-based recommendation models. Meanwhile, although image features are also key signals in recommender systems, there is currently a lack of research on recommendation models that are primarily based on raw image pixels. The lack of large-scale datasets containing raw images in visually driven recommendation scenarios has been a significant barrier to the development of this research direction. To address this challenge, we introduce PixelRec, a comprehensive dataset of cover images collected from a video streaming platform. With approximately 200 million user image interactions, 30 million users, and 400,000 high-resolution short video cover images, PixelRec facilitates the development, benchmarking, and analysis of various image pixel based recommendation models. Leveraging this dataset, we establish a accessible pipeline to implement a series of vision-based recommendation models, providing extensive benchmark results for them. Our contributions include the PixelRec dataset, baseline algorithms, operational pipeline, exploratory findings, and the PixelRec benchmark. We believe PixelRec will significantly advance research on recommendation models based on image content and foster fruitful collaboration between the fields of recommender systems and computer vision. The dataset, code, and documents are made available at https://github.com/westlake-repl/PixelRec.

Adapters, a plug-in neural network module with some tunable parameters, have emerged as a parameter-efficient transfer learning technique for adapting pre-trained models to downstream tasks, especially for natural language processing (NLP) and computer vision (CV) fields. Meanwhile, learning recommendation models directly from raw item modality features --- e.g., texts of NLP and images of CV --- can enable effective and transferable recommender systems (called TransRec). In view of this, a natural question arises:can adapter-based learning techniques achieve parameter-efficient TransRec with good performance?

The recommender systems on online platforms assist users in finding personalized information, yet this also leads to the issue of limited diversity, potentially giving rise to societal issues such as filter bubbles. Despite significant progress in diversified recommendation algorithms, they have not been extensively experimented with and evaluated for effectiveness in large-scale, full-stage industrial recommender systems. Specifically, industrial recommenders usually consist of three stages of matching, ranking, and re-ranking, in which specific characteristics lead to critical challenges for promoting both recommendation diversity and user engagement. First, user interests are partially observed due to only relevance maximization. Second, item-side feature-aware bias causes imbalanced recommendations. Last, the impact of diversity perception on user engagement stresses the necessity of explicit diversity modeling. To address these challenges in industrial systems, in this work, we deploy several existing diversified algorithms in a real-world short-video platform, including exploration-exploitation, feature-aware debiasing, and diversity optimization. We conduct large-scale online A/B testing for evaluation via online metrics of user engagement and recommendation diversity. Performance improvement across full stages demonstrates the effectiveness of these simple solutions. From comparing performance across different stages and algorithms, we identify that the ranking stage is the most suitable for real-world deployment, and the combination of debiasing and diversity optimization is a promising direction in terms of diversified recommendations. This work provides experiential guidance for the large-scale deployment of diversified algorithms and the construction of a more inclusive platform on the Web.

Short-video recommendation is one of the most important recommendation applications in today's industrial information systems. Compared with other recommendation tasks, the enormous amount of feedback is the most typical characteristic. Specifically, in short-video recommendation, the easiest-to-collect user feedback is theskipping behavior, which leads to two critical challenges for the recommendation model. First, the skipping behavior reflects implicit user preferences, and thus, it is challenging for interest extraction. Second, this kind of special feedback involves multiple objectives, such as total watching time and skipping rate, which is also very challenging. In this paper, we present our industrial solution in Kuaishou1, which serves billion-level users every day. Specifically, we deploy a feedback-aware encoding module that extracts user preferences, taking the impact of context into consideration. We further design a multi-objective prediction module which well distinguishes the relation and differences among different model objectives in the short-video recommendation. We conduct extensive online A/B tests, along with detailed and careful analysis, which verify the effectiveness of our solution.

Sequential recommendation is one of the most important tasks in recommender systems, which aims to recommend the next interacted item with historical behaviors as input. Traditional sequential recommendation always mainly considers the collected positive feedback such as click, purchase, etc. However, in short-video platforms such as TikTok, video viewing behavior may not always represent positive feedback. Specifically, the videos are played automatically, and users passively receive the recommended videos. In this new scenario, users passively express negative feedback by skipping over videos they do not like, which provides valuable information about their preferences. Different from the negative feedback studied in traditional recommender systems, this passive-negative feedback can reflect users’ interests and serve as an important supervision signal in extracting users’ preferences. Therefore, it is essential to carefully design and utilize it in this novel recommendation scenario. In this work, we first conduct analyses based on a large-scale real-world short-video behavior dataset and illustrate the significance of leveraging passive feedback. We then propose a novel method that deploys the sub-interest encoder, which incorporates positive feedback and passive-negative feedback as supervision signals to learn the user’s current active sub-interest. Moreover, we introduce an adaptive fusion layer to integrate various sub-interests effectively. To enhance the robustness of our model, we then introduce a multi-task learning module to simultaneously optimize two kinds of feedback – passive-negative feedback and traditional randomly-sampled negative feedback. The experiments on two large-scale datasets verify that the proposed method can significantly outperform state-of-the-art approaches. The code is released at https://github.com/tsinghua-fib-lab/RecSys2023-SINE to benefit the community.

Recommendation models that utilize unique identities (IDs for short) to represent distinct users and items have been state-of-the-art (SOTA) and dominated the recommender systems (RS) literature for over a decade. Meanwhile, the pre-trained modality encoders, such as BERT [9] and Vision Transformer [11], have become increasingly powerful in modeling the raw modality features of an item, such as text and images. Given this, a natural question arises: can a purely modality-based recommendation model (MoRec) outperforms or matches a pure ID-based model (IDRec) by replacing the itemID embedding with a SOTA modality encoder? In fact, this question was answered ten years ago when IDRec beats MoRec by a strong margin in both recommendation accuracy and efficiency.