Related papers: Online Distillation-enhanced Multi-modal Transform…

The explosion of multimedia data in information-rich environments has intensified the challenges of personalized content discovery, positioning recommendation systems as an essential form of passive data management. Multimodal sequential…

Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data.…

The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data, prompting the development of Dataset Distillation methods to address the challenges of managing large datasets.…

Sequential Recommendation (SR) aims to predict future user-item interactions based on historical interactions. While many SR approaches concentrate on user IDs and item IDs, the human perception of the world through multi-modal signals,…

ID-based Recommender Systems (RecSys), where each item is assigned a unique identifier and subsequently converted into an embedding vector, have dominated the designing of RecSys. Though prevalent, such ID-based paradigm is not suitable for…

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Multimodal intent understanding is a significant research area that requires effective leveraging of multiple modalities to analyze human language. Existing methods face two main challenges in this domain. Firstly, they have limitations in…

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

Federated learning enables the creation of a powerful centralized model without compromising data privacy of multiple participants. While successful, it does not incorporate the case where each participant independently designs its own…

Multimodal learning has increasingly become a focal point in research, primarily due to its ability to integrate complementary information from diverse modalities. Nevertheless, modality imbalance, stemming from factors such as insufficient…

Despite its breakthrough in classification problems, Knowledge distillation (KD) to recommendation models and ranking problems has not been studied well in the previous literature. This dissertation is devoted to developing knowledge…

To accommodate real-world dynamics, artificial intelligence systems need to cope with sequentially arriving content in an online manner. Beyond regular Continual Learning (CL) attempting to address catastrophic forgetting with offline…

Today, the acquisition of various behavioral log data has enabled deeper understanding of customer preferences and future behaviors in the marketing field. In particular, multimodal deep learning has achieved highly accurate predictions by…

In modern e-commerce, item content features in various modalities offer accurate yet comprehensive information to recommender systems. The majority of previous work either focuses on learning effective item representation during modelling…

Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generalize better. It can…

Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in…

This article presents a novel approach to multimodal recommendation systems, focusing on integrating and purifying multimodal data. Our methodology starts by developing a filter to remove noise from various types of data, making the…

Personalized recommendation serves as a ubiquitous channel for users to discover information tailored to their interests. However, traditional recommendation models primarily rely on unique IDs and categorical features for user-item…

Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…