Many classification problems require classifiers to assign each single document into more than one category, which is called multilabelled classification. The categories in such problems usually are neither conditionally independent from each other nor mutually exclusive, therefore it is not trivial to directly employ state-of-theart classification algorithms without losing information of relation among categories. In this paper, we explore correlations among categories with maximum entropy method and derive a classification algorithm for multi-labelled documents. Our experiments show that this method significantly outperforms the combination of single label approach.

No abstract

We propose a method for discovering the dependency relationships between the topics of documents shared in social networks using the latent social interactions, attempting to answer the question: given a seemingly new topic, from where does this topic evolve?. In particular, we seek to discover the pair-wise probabilistic dependency in topics of documents which associate social actors from a latent social network, where these documents are being shared. By viewing the evolution of topics as a Markov chain, we estimate a Markov transition matrix of topics by leveraging social interactions and topic semantics. Metastable states in a Markov chain are applied to the clustering of topics. Applied to the CiteSeer dataset, a collection of documents in academia, we show the trends of research topics, how research topics are related and which are stable. We also show how certain social actors, authors, impact these topics and propose new ways for evaluating author impact.

No abstract

Emerging tumor treatment demands high sensitivity and high-spatial resolution diagnosis in combination with targeted therapy. Here, we report that iodine-rich polymersomes (I-PS) enable versatile single-photon emission computed tomography (SPECT)/computed tomography (CT) dual-modal imaging and potent radioisotope therapy for breast cancer in vivo. Interestingly, I-PS could be easily and stably labeled with radioiodine, 125I and 131I. Dynamic light scattering and transmission electron microscopy showed that 125I-PS had a size of 106 nm and vesicular morphology, similar to those of the parent I-PS. Methyl thiazolyl tetrazolium assays displayed that I-PS and 125I-PS were noncytotoxic, whereas 131I-PS caused significant death of 4T1 cells at 5 mg PS/mL with a radioactivity of 12 μCi. Pharmacokinetic and biodistribution studies showed that 125I-PS has a prolonged circulation and distributes mainly in tumor and the reticuloendothelial system. The intravenous injection of 125I-PS to 4T1 murine breast tumor-bearing mice allowed simultaneous high sensitivity and high-spatial resolution imaging of tumor by SPECT and CT, respectively. The therapeutic studies revealed that 131I-PS could effectively retard the growth of 4T1 breast tumor and significantly prolong mice survival time. The hematoxylin and eosin staining assay proved that 131I-PS induced tumor cell death. I-PS emerges as a robust and versatile platform for dual-modal imaging and targeted radioisotope therapy.

No abstract

Sequential recommendation systems alleviate the problem of information overload, and have attracted increasing attention in the literature. Most prior works usually obtain an overall representation based on the user’s behavior sequence, which can not sufficiently reflect the multiple interests of the user. To this end, we propose a novel method called PIMI to mitigate this issue. PIMI can model the user’s multi-interest representation effectively by considering both the periodicity and interactivity in the item sequence. Specifically, we design a periodicity-aware module to utilize the time interval information between user’s behaviors. Meanwhile, an ingenious graph is proposed to enhance the interactivity between items in user’s behavior sequence, which can capture both global and local item features. Finally, a multi-interest extraction module is applied to describe user’s multiple interests based on the obtained item representation. Extensive experiments on two real-world datasets Amazon and Taobao show that PIMI outperforms state-of-the-art methods consistently.

No abstract