Due to the efficiency of learning relationships and complex structures hidden in data, graph-oriented methods have been widely investigated and achieve promising performance. Generally, in the field of multi-view learning, these algorithms construct informative graph for each view, on which the following clustering or classification procedure are based. However, in many real-world data sets, original data always contain noises and outlying entries that result in unreliable and inaccurate graphs, which cannot be ameliorated in the previous methods. In this paper, we propose a novel multi-view learning model which performs clustering/semi-supervised classification and local structure learning simultaneously. The obtained optimal graph can be partitioned into specific clusters directly. Moreover, our model can allocate ideal weight for each view automatically without explicit weight definition and penalty parameters. An efficient algorithm is proposed to optimize this model. Extensive experimental results on different real-world data sets show that the proposed model outperforms other state-of-the-art multi-view algorithms.

Due to the efficiency of learning relationships and complex structures hidden in data, graph-oriented methods have been widely investigated and achieve promising performance in multi-view learning. Generally, these learning algorithms construct informative graph for each view or fuse different views to one graph, on which the following procedure are based. However, in many real world dataset, original data always contain noise and outlying entries that result in unreliable and inaccurate graphs, which cannot be ameliorated in the previous methods. In this paper, we propose a novel multi-view learning model which performs clustering/semi-supervised classification and local structure learning simultaneously. The obtained optimal graph can be partitioned into specific clusters directly. Moreover, our model can allocate ideal weight for each view automatically without additional weight and penalty parameters. An efficient algorithm is proposed to optimize this model. Extensive experimental results on different real-world datasets show that the proposed model outperforms other state-of-the-art multi-view algorithms.

Background: Chemoresistance is one key factor for the failure of cisplatin (CDDP)-based therapy in colorectal cancer (CRC). Although circular RNAs (circRNAs) are associated with chemoresistance development, the role and mechanism of hsa_circ_0071589 (circ_0071589) in the development of CDDP resistance in CRC remain unclear. Methods: CDDP-resistant and sensitive CRC samples were collected. CDDP-resistant HCT116/CDDP and LOVO/CDDP cells were established. The levels of circ_0071589, microRNA (miR)-526b-3p and Krüppel-like factor 12 (KLF12) were detected via quantitative reverse transcription polymerase chain reaction, Western blot or immunohistochemistry. Cell viability, proliferation, cycle process, apoptosis, migration and invasion were examined via Cell Counting Kit-8, flow cytometry, transwell assay and Western blot. The association between miR-526b-3p and circ_0071589 or KLF12 was predicted by starBase, and explored via dual-luciferase reporter assay and RNA immunoprecipitation. The effect of circ_0071589 on CDDP resistance in CRC in vivo was investigated using a xenograft model. Results: Circ_0071589 level was upregulated in CDDP-resistant CRC tissue samples and cell lines. Circ_0071589 knockdown inhibited CDDP resistance, proliferation, migration and invasion, and promoted apoptosis in CDDP-resistant CRC cells. Circ_0071589 was a sponge for miR-526b-3p. MiR-526b-3p knockdown reversed the role of circ_0071589 inhibition in CDDP resistance. MiR-526b-3p suppressed CDDP resistance by directly targeting KLF12. Circ_0071589 regulated KLF12 expression through modulating miR-526b-3p. Circ_0071589 knockdown aggravated CDDP-induced reduction of xenograft tumor growth by upregulating miR-526b-3p and decreasing KLF12. Conclusion: Knockdown of circ_0071589 repressed CDDP resistance in CDDP-resistant CRC cells by regulating the miR-526b-3p/KLF12 axis.

Sequential recommender systems aim to model users’ evolving interests from their historical behaviors, and hence make customized time-relevant recommendations. Compared with traditional models, deep learning approaches such as CNN and RNN have achieved remarkable advancements in recommendation tasks. Recently, the BERT framework also emerges as a promising method, benefited from its self-attention mechanism in processing sequential data. However, one limitation of the original BERT framework is that it only considers one input source of the natural language tokens. It is still an open question to leverage various types of information under the BERT framework. Nonetheless, it is intuitively appealing to utilize other side information, such as item category or tag, for more comprehensive depictions and better recommendations. In our pilot experiments, we found naive approaches, which directly fuse types of side information into the item embeddings, usually bring very little or even negative effects. Therefore, in this paper, we propose the NOn-inVasive self-Attention mechanism (NOVA) to leverage side information effectively under the BERT framework. NOVA makes use of side information to generate better attention distribution, rather than directly altering the item embeddings, which may cause information overwhelming. We validate the NOVA-BERT model on both public and commercial datasets, and our method can stably outperform the state-of-the-art models with negligible computational overheads.

No abstract