There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Three parallel algorithms for classical molecular dynamics are presented. The first assigns each processor a fixed subset of atoms; the second assigns each a fixed subset of inter-atomic forces to compute; the third assigns each a fixed spatial region. The algorithms are suitable for molecular dynamics models which can be difficult to parallelize efficiently—those with short-range forces where the neighbors of each atom change rapidly. They can be implemented on any distributed-memory parallel machine which allows for message-passing of data between independently executing processors. The algorithms are tested on a standard Lennard-Jones benchmark problem for system sizes ranging from 500 to 100,000,000 atoms on several parallel supercomputers--the nCUBE 2, Intel iPSC/860 and Paragon, and Cray T3D. Comparing the results to the fastest reported vectorized Cray Y-MP and C90 algorithm shows that the current generation of parallel machines is competitive with conventional vector supercomputers even for small problems. For large problems, the spatial algorithm achieves parallel efficiencies of 90% and a 1840-node Intel Paragon performs up to 165 faster than a single Cray C9O processor. Trade-offs between the three algorithms and guidelines for adapting them to more complex molecular dynamics simulations are also discussed.

Fast parallel algorithms for short-range molecular dynamics

The increasing volume of data in modern business and science calls for more complex and sophisticated tools. Although advances in data mining technology have made extensive data collection much easier, it's still always evolving and there is a constant need for new techniques and tools that can help us transform this data into useful information and knowledge. Since the previous edition's publication, great advances have been made in the field of data mining. Not only does the third of edition of Data Mining: Concepts and Techniques continue the tradition of equipping you with an understanding and application of the theory and practice of discovering patterns hidden in large data sets, it also focuses on new, important topics in the field: data warehouses and data cube technology, mining stream, mining social networks, and mining spatial, multimedia and other complex data. Each chapter is a stand-alone guide to a critical topic, presenting proven algorithms and sound implementations ready to be used directly or with strategic modification against live data. This is the resource you need if you want to apply today's most powerful data mining techniques to meet real business challenges. * Presents dozens of algorithms and implementation examples, all in pseudo-code and suitable for use in real-world, large-scale data mining projects. * Addresses advanced topics such as mining object-relational databases, spatial databases, multimedia databases, time-series databases, text databases, the World Wide Web, and applications in several fields. *Provides a comprehensive, practical look at the concepts and techniques you need to get the most out of real business data

/pdf/data-mining-concepts-and-techniques-4dtvdfkvmi.pdf

Data Mining: Concepts and Techniques

A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data-labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression, and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.

/pdf/a-survey-on-transfer-learning-1hjmu3otql.pdf

A Survey on Transfer Learning

Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges. We propose a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning. More importantly, we provide insights on cache access patterns, data compression and sharding to build a scalable tree boosting system. By combining these insights, XGBoost scales beyond billions of examples using far fewer resources than existing systems.

/pdf/xgboost-a-scalable-tree-boosting-system-48ocu6x4c7.pdf

XGBoost: A Scalable Tree Boosting System

Operating the Internet infrastructure in an energy-efficient manner ("Green Internet") becomes a challenging issue in most recent years with the recognition of significant energy consumption due to its large scale. Yet a limited number of contributions are available to address the issue mainly through putting idle routers and links into sleep mode, at the price of low global resource utilization efficiency and degraded network performance. This paper follows the same line of research but investigates an optimal solution of configuring IP network topology to minimize the number of active routers and links, and hence energy consumption, whilst keep the interference on network operation minimal. An optimal energy-efficient network model along with a heuristic algorithm is proposed for identifying the network elements in sleep mode to attain approximately the best trade-off between the energy-efficiency and performance degradation. Numerical experiments are carried out to assess the solution for a range of network and load scenarios and the results clearly demonstrate its effectiveness.

Configuring network topology towards energy-efficient IP networks

Federated learning (FL) is a privacy-preserving paradigm that collaboratively train machine learning models with distributed data stored in different silos without exposing sensitive information. Different from most existing FL approaches requiring data from different parties share either the same feature space or sample ID space, federated transfer learning (FTL), which is a recently proposed FL concept, is designed for situations where data from different parties differ not only in samples but also in feature space. However, like most traditional FL approaches, FTL methods also suffer from issues caused by insufficiency of overlapping data. In this paper, we propose a novel FTL framework referred to as Semi-Supervised Federated Heterogeneous Transfer Learning (SFHTL) to leverage on the unlabeled non-overlapping samples to reduce model overfitting as a result of insufficient overlapping training samples in FL scenarios. Unlike existing FTL approaches, SFHTL makes use of non-overlapping samples from all parties to expand the training set for each party to improve local model performance. Through extensive experimental evaluation based on real-world datasets, we demonstrate significant advantages of SFHTL over state-of-the-art approaches. 

Semi-Supervised Federated Heterogeneous Transfer Learning

Association Rule Mining algorithms operate on a data matrix to derive association rule, discarding the quantities of the items, which contains valuable information. In order to make full use of the knowledge inherent in the quantities of the items, an extension named Ratio Rules [6] is proposed to capture the quantitative association. However, the approach, which is addressed in [6], is mainly based on Principle Component Analysis (PCA) and as a result, it cannot guarantee that the ratio coefficient is non-negative. This may lead to serious problems in the association rules' application. In this paper, a new method, called Principal Non-negative Sparse Coding (PNSC), is provided for learning the associations between itemsets in the form of Ratio Rules. Experiments on several datasets illustrate that the proposed method performs well for the purpose of discovering latent associations between itemsets in large datasets.

Mining quantitative associations in large database

In generative dialog systems, learning representations for the dialog context is a crucial step in generating high quality responses. The dialog systems are required to capture useful and compact information from mutually dependent sentences such that the generation process can effectively attend to the central semantics. Unfortunately, existing methods may not effectively identify importance distributions for each lower position when computing an upper level feature, which may lead to the loss of information critical to the constitution of the final context representations. To address this issue, we propose a transfer learning based method named transfer hierarchical attention network (THAN). The THAN model can leverage useful prior knowledge from two related auxiliary tasks, i.e., keyword extraction and sentence entailment, to facilitate the dialog representation learning for the main dialog generation task. During the transfer process, the syntactic structure and semantic relationship from the auxiliary tasks are distilled to enhance both the word-level and sentence-level attention mechanisms for the dialog system. Empirically, extensive experiments on the Twitter Dialog Corpus and the PERSONA-CHAT dataset demonstrate the effectiveness of the proposed THAN model compared with the state-of-the-art methods.

/pdf/transfer-hierarchical-attention-network-for-generative-274lxgr8c4.pdf

Qiang Yang

Papers

Configuring network topology towards energy-efficient IP networks

Semi-Supervised Federated Heterogeneous Transfer Learning

Mining quantitative associations in large database

Transfer Hierarchical Attention Network for Generative Dialog System

Construction of a Rapid Photothermal Antibacterial Silk Fabric via QCS-Guided In Situ Deposition of CuSNPs