Search Results

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on various visual-language understanding and generation tasks. However, MLLMs occasionally generate content inconsistent with the given images, which is known as "...

Recommender system usually suffers from severe <italic>popularity bias</italic> &#x2014; the collected interaction data usually exhibits quite imbalanced or even long-tailed distribution over items. Such skewed distribution may result from the users&#...

Recent years have witnessed the great successes of embedding-based methods in recommender systems. Despite their decent performance, we argue one potential limitation of these methods — the embedding magnitude has not been explicitly modulated, which ...

Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks. Although recently have witnessed a surge of work on KGC, they are still insufficient to ...

Recommender systems have shown great potential to solve the information explosion problem and enhance user experience in various online applications. To tackle data sparsity and cold start problems in recommender systems, researchers propose knowledge ...

Named entity recognition (NER) systems have been widely researched and applied for decades. Most NER systems rely on high quality annotations, but in some specific domains, annotated data is usually imperfect, typically including incomplete ...

Link prediction is a fundamental problem with a wide range of applications in various domains, which predicts the links that are not yet observed or the links that may appear in the future. Most existing works in this field only focus on modeling a single ...

Aligning heterogeneous online social networks is a highly beneficial task proposed in recent years. It targets at automatically aligning accounts from multiple networks by whether they are held by the same natural person. Aligning the networks can ...

Most people now participate in more than one online social network OSN. However, the alignment indicating which accounts belong to same natural person is not revealed. Aligning these isolated networks can provide united environment for users and help to ...

An accurate and comprehensive user modeling technique is crucial for the quality of recommender systems. Traditionally, we model user preferences using only actions from the target site and may suffer from cold-start problem. As nowadays people normally ...

Conformity has a strong influence to user behaviors, even in online environment. When surfing online, users are usually flooded with others' opinions. These opinions implicitly contribute to the user's ongoing behaviors. However, there is no research ...

Online review sites are widely used for various domains including movies and restaurants. These sites now have strong influences towards users during purchasing processes. There exist plenty of research works for review sites on various aspects, ...

This paper describes our solution to ICDM 2015's contest. The challenge is to recover cross-device connections, i.e. identifying device-cookie pairs that is used by the same natural person. To tackle this task, we first model the privateness of each IP, ...

Microblogging websites such as Twitter and Chinese Sina Weibo contain large amounts of microblogs posted by users. Many of these microblogs are highly sensitive to the important real-world events and correlated to the news events. Thus, microblogs from ...