Machine Learning for 5G and Beyond:From ModelBased to Data-Driven Mobile Wireless Networks

During the past few decades,mobile wireless communications have experienced four generations of technological revolution,namely from 1 G to 4 G,and the deployment of the latest 5 G networks is expected to take place in 2019.One fundamental question is how we can push forward the development of mobile wireless communications while it has become an extremely complex and sophisticated system.We believe that the answer lies in the huge volumes of data produced by the network itself,and machine learning may become a key to exploit such information.In this paper,we elaborate why the conventional model-based paradigm,which has been widely proved useful in pre-5 G networks,can be less efficient or even less practical in the future 5 G and beyond mobile networks.Then,we explain how the data-driven paradigm,using state-of-the-art machine learning techniques,can become a promising solution.At last,we provide a typical use case of the data-driven paradigm,i.e.,proactive load balancing,in which online learning is utilized to adjust cell configurations in advance to avoid burst congestion caused by rapid traffic changes.

Synthesis of α-hydroxy ketones by copper（Ⅰ）-catalyzed hydration of propargylic alcohols: CO2 as a cocatalyst under atmospheric pressure

Inexpensive and efficient Cu(Ⅰ) catalysis is reported for the synthesis of α-hydroxy ketones from propargylic alcohols, CO2, and water via tandem carboxylative cyclization and nucleophilic addition reaction. Notably, hydration of propargylic alcohols can be carried out smoothly under atmospheric CO2 pressure, generating a series of α-hydroxy ketones efficiently and selectively. This strategy shows great potential for the preparation of valuable α-hydroxy ketones by using CO2 as a crucial cocatalyst under mild conditions.

Minimal Gated Unit for Recurrent Neural Networks

Recurrent neural networks （RNN） have been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN learning is a difficult task, partly because there are many competing and complex hidden units, such as the long short-term memory （LSTM） and the gated recurrent unit （GRU）. We propose a gated unit for RNN, named as minimal gated unit （MCU）, since it only contains one gate, which is a minimal design among all gated hidden units. The design of MCU benefits from evaluation results on LSTM and GRU in the literature. Experiments on various sequence data show that MCU has comparable accuracy with GRU, but has a simpler structure, fewer parameters, and faster training. Hence, MGU is suitable in RNN＇s applications. Its simple architecture also means that it is easier to evaluate and tune, and in principle it is easier to study MGU＇s properties theoretically and empirically.

Structural diversity for decision tree ensemble learning

Decision trees are a kind of off-the-shelf predictive models, and they have been successfully used as the base learners in ensemble learning. To construct a strong classi- fier ensemble, the individual classifiers should be accurate and diverse. However, diversity measure remains a mystery although there were many attempts. We conjecture that a deficiency of previous diversity measures lies in the fact that they consider only behavioral diversity, i.e., how the classifiers behave when making predictions, neglecting the fact that classifiers may be potentially different even when they make the same predictions. Based on this recognition, in this paper, we advocate to consider structural diversity in addition to behavioral diversity, and propose the TMD （tree matching diversity） measure for decision trees. To investigate the usefulness of TMD, we empirically evaluate performances of selective ensemble approaches with decision forests by incorporating different diversity measures. Our results validate that by considering structural and behavioral diversities together, stronger ensembles can be constructed. This may raise a new direction to design better diversity measures and ensemble methods.

Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models

Researchers often summarize their work in the form of scientific posters.Posters provide a coherent and efficient way to convey core ideas expressed in scientific papers.Generating a good scientific poster,however,is a complex and time-consuming cognitive task,since such posters need to be readable,informative,and visually aesthetic.In this paper, for the first time,we study the challenging problem of learning to generate posters from scientific papers.To this end,a data-driven framework,which utilizes graphical models,is proposed.Specifically,given content to display,the key elements of a good poster,including attributes of each panel and arrangements of graphical elements,are learned and inferred from data.During the inference stage,the maximum a posterior (MAP)estimation framework is employed to incorporate some design principles.In order to bridge the gap between panel attributes and the composition within each panel,we also propose a recursive page splitting algorithm to generate the panel layout for a poster.To learn and validate our model,we collect and release a new benchmark dataset,called NJU-Fudan Paper-Poster dataset,which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes.Qualitative and quantitative results indicate the effectiveness of our approach.

Crowd intelligence in AI 2.0 era

The Internet based cyber-physical world has profoundly changed the information environment for the development of artificial intelligence(AI), bringing a new wave of AI research and promoting it into the new era of AI 2.0. As one of the most prominent characteristics of research in AI 2.0 era, crowd intelligence has attracted much attention from both industry and research communities. Specifically, crowd intelligence provides a novel problem-solving paradigm through gathering the intelligence of crowds to address challenges. In particular, due to the rapid development of the sharing economy, crowd intelligence not only becomes a new approach to solving scientific challenges, but has also been integrated into all kinds of application scenarios in daily life, e.g., online-tooffline(O2O) application, real-time traffic monitoring, and logistics management. In this paper, we survey existing studies of crowd intelligence. First, we describe the concept of crowd intelligence, and explain its relationship to the existing related concepts, e.g., crowdsourcing and human computation. Then, we introduce four categories of representative crowd intelligence platforms. We summarize three core research problems and the state-of-the-art techniques of crowd intelligence. Finally, we discuss promising future research directions of crowd intelligence.

Boosting and margin theory

Many researchers have worked on the ex- planation of AdaBoost＇s good experimental results in theory. Some work give an upper bound of generaliza- tion error in terms of the margin distribution function, while Breiman gave a sharper generalization error bound based on minimum margin. He also developed the arc- gv algorithm to maximize the minimum margin, then made the minimum margin larger than AdaBoost. How- ever, its empirical results are even worse than AdaBoost. Therefore, is the minimum margin bound not practi- cal？ This paper gives a new concept called Equilibrium margin （Emargin） and proves a new generalization er- ror bound using Emargin, which is always better than minimum margin bound. In addition, we show Emargin is a good indicator of generalization. Then, we conduct experiments showing that the Emargin of AdaBoost is larger than arc-gv, but the generalization error of Ada- Boost is usually better.

Rehearsal:learning from prediction to decision

Machine learning[1]studies focus mostly on prediction,where a model is built from a set of observational data formaking correct predictions on unseen instances.It has beenaddressed very well by modem techniques such as deeplearming[2],though some issues,c.g,open environmentmachine learning[3],remain to be developed.

Efficient and Recyclable Cobalt(Ⅱ)/Ionic Liquid Catalytic System for CO2 Conversion to Prepare 2-Oxazolinones at Atmospheric Pressure

Summary of main observation and conclusion Converting CO2 into value-added chemicals represents a promising way to alleviate the CO2 derived environmental issues,for which the development of catalysts with high efficiency and recyclability is very desirable.Herein,the catalytic system by combining cobalt source and ionic liquid(IL)has been developed as the efficacious and recyclable catalyst for the carboxylative cyclization of propargylic amine and CO2 to prepare 2-oxazolinones.In this protocol,various propargylic amines were successfully transformed into the corresponding 2-oxazolinones with CoBr2 and diethylimidazolium acetate([EEIM][OAc])as the catalyst under atmospheric CO2 pressure.It is worth noting that the turnover number(TON)of this transformation can be up to 1740,presumably being attributed to the cooperative effect of the cobalt and IL.Furthermore,the existence of IL enables the catalytic system to be easily recycled to 10 times without losing its activity.

Ionic Liquid-Modified Porous Organometallic Polymers as Efficient and Selective Photocatalysts for Visible-Light-Driven CO_(2) Reduction

In the photoreduction of CO_(2) to CO,the competitive H2 evolution is always inevitable due to the approximate reduction potentials of H+/H2 and CO_(2)/CO,which results in poor selectivity for CO production.Herein,imidazolium-type ionic liquid-(IL-)modified rhenium bipyridine-based porous organometallic polymers(Re-POMP-IL)were designed as efficient and selective photocatalysts for visible-light CO_(2) photoreduction to CO based on the affinity of IL with CO_(2).Photoreduction studies demonstrated that CO_(2) photoreduction promoted by Re-POMP-IL functioning as the catalyst exhibits excellent CO selectivity up to 95.5%and generate 40.1 mmol CO/g of Re-POMP-IL1.0(obtained by providing equivalent[(5,5′-divinyl-2,2′-bipyridine)Re(CO)_(3)Cl]and 3-ethyl-1-vinyl-1H-imidazol-3-ium bromide)at 12 h,outperforming that attained with the corresponding Re-POMP analogue without IL,which highlights the crucial role of IL.Notably,CO_(2) adsorption,light harvesting,and transfer of photogenerated charges as key steps for CO_(2)RR were studied by employing POMPs modified with different amounts of IL as photocatalysts,among which the CO_(2) affinity as an important factor for POMPs catalyzed CO_(2) reduction is revealed.Overall,this work provides a practical pathway to improve the CO_(2) photoreduction efficiency and CO selectivity by employing IL as a regulator.

Learnware： on the future of machine learning

Current machine learning techniques have achieved great success; however, there are many deficiencies. First, to train a strong model, a large amount of training examples are required, whereas collecting the data, particularly data with labels, is expensive or even difficult in many real tasks. Second, once a model has been trained, if environment changes, which often happens in real tasks, the model can hardly perform well or even become useless. Third,

Launch of the Excellent Young Computer Scientists Forum

Since Volume 10, 2016, Frontiers of Computer Science established an "NSFC Excellent Young Scholars Forum", which aims to publishing articles from recipients of the NSFC (National Science Foundation of China) Excellent Young Scholars Program. During the past three years, 37 articles have been published and this forum has received very positive feedbacks from readers.

Metatranscriptome of the protistan community in Reticufitermes flaviceps

The hindgut of lower termites harbors various symbiotic protists, which per- form varied functions in lignocellulose decomposition. As termites are social insects, the species and numbers of these flagellated protists in the termite gut vary among the different castes. Juvenile hormones （JHs） can regulate caste differentiation in termites. In this study, we used the juvenile hormone analog fenoxycarh to induce termite workers （Reticulitermesflaviceps） to differentiate into pre-soldiers. A metatranscriptomic investigation of the protistan community was then performed by 454 pyrosequencing. From a thorough analysis based on 597 312 generated reads, we found that the starch and sucrose metabolism pathway was the most abundant pathway across the metatranscriptome. The current study demonstrates that the metatranscriptome of the protistan community in termites contains an abundance of lignocellulase, which plays a vital role in termite nutrition.

Launch of the NSFC Excellent Young Scholars Forum

In 2012, the National Natural Science Foundation of China （NSFC） launched the Excellent Young Scholars （EYS） Pro- gram. As its name suggests, this program aims to recognize and support excellent young scholars in the fields of science and engineering. This program is similar to the NSF Career Award in the United States, and the competition is very tough： only a very limited number of applicants can get through. Each awardee will receive a fund of one million CNY for a three-year term.With such generous support, awardees are expected to do more excellent research and grow up quickly as distinguished young scholars.