Qiang Yang

Kai Chen

Privacy-preserving computing aims to protect the personal information of users while capitalizing on the possibilities unlocked by big data. This practical introduction for students, researchers, and industry practitioners is the first cohesive and systematic presentation of the field's advances over four decades. The book shows how to use privacy-preserving computing in real-world problems in data analytics and AI, and includes applications in statistics, database queries, and machine learning. The book begins by introducing cryptographic techniques such as secret sharing, homomorphic encryption, and oblivious transfer, and then broadens its focus to more widely applicable techniques such as differential privacy, trusted execution environment, and federated learning. The book ends with privacy-preserving computing in practice in areas like finance, online advertising, and healthcare, and finally offers a vision for the future of the field.

for Big Data Analytics and AI

Privacy-preserving Computing

Chee Seng Chan

Lixin Fan

Machine learning (ML) models, especially large pretrained deep learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR). Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model’s owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, natural language processing and reinforcement learning. This book covers the motivations, fundamentals, techniques and protocols for protecting ML models using watermarking. Furthermore, it showcases cutting-edge work in e.g. model watermarking, signature and passport embedding and their use cases in distributed federated learning settings.

Techniques, Protocols and Applications

Digital Watermarking for Machine Learning Model

Charles Ling

What is it like to be a researcher or a scientist? For young people, including graduate students and junior faculty members in universities, how can they identify good ideas for research? How do they conduct solid research to verify and realize their new ideas? How can they formulate their ideas and research results into high-quality articles, and publish them in highly competitive journals and conferences? What are effective ways to supervise graduate students so that they can establish themselves quickly in their research careers? In this book, Ling and Yang answer these questions in a step-by-step manner with specific and concrete examples from their first-hand research experience. Table of Contents: Acknowledgments / Preface / Basics of Research / Goals of Ph.D. Research / Getting Started: Finding New Ideas and Organizing Your Plans / Conducting Solid Research / Writing and Publishing Papers / Misconceptions and Tips for Paper Writing / Writing and Defending a Ph.D. Thesis / Life After Ph.D. / Summary / References / Author Biographies

A Guide to Successful Master's and Ph.D. Degrees in Science & Engineering

Crafting Your Research Future

Jian Pei

João Gama

Xue Li

Ronghuai Huang

Xiaofeng Meng

This volume contains the proceedings of the International Conference on Advanced Data Mining and Applications (ADMA 2009), held in Beijing, China, during August 17–19, 2009. We are pleased to have a very strong program. Acceptance into the conference proceedings was extremely competitive. From the 322 submissions from 27 countries and regions, the Program Committee selected 34 full papers and 47 short papers for presentation at the conference and inclusion in the proceedings. The c- tributed papers cover a wide range of data mining topics and a diverse spectrum of interesting applications. The Program Committee worked very hard to select these papers through a rigorous review process and extensive discussion, and finally c- posed a diverse and exciting program for ADMA 2009. An important feature of the main program was the truly outstanding keynote spe- ers program. Edward Y. Chang, Director of Research, Google China, gave a talk titled "Confucius and 'Its' Intelligent Disciples". Being right in the forefront of data mining applications to the world's largest knowledge and data base, the Web, Dr. Chang - scribed how Google's Knowledge Search product help to improve the scalability of machine learning for Web-scale applications. Charles X. Ling, a seasoned researcher in data mining from the University of Western Ontario, Canada, talked about his in- vative applications of data mining and artificial intelligence to gifted child education.

5th International Conference, ADMA 2009, Chengdu, China, August 17-19, 2009, Proceedings

Advanced Data Mining and Applications

Ah-Hwee Tan

Jinyan Li

This book constitutes the refereed proceedings of the International Workshop on Data Mining for Biomedical Applications, BioDM 2006, held in Singapore in conjunction with the 10th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2006). The 14 revised full papers presented together with one keynote talk were carefully reviewed and selected from 35 submissions. The papers are organized in topical sections

PAKDD 2006 Workshop, BioDM 2006, Singapore, April 9, 2006, Proceedings

Data Mining for Biomedical Applications

Ben Hutchinson

Graham Cormode

Yang Liu

David Evans

Han Yu

Ramesh Raskar

Mehryar Mohri

Zheng Xu

Rachel Cummings

Dawn Song

Mehdi Bennis

Peter Kairouz

H. Brendan McMahan

Brendan Avent

Aurélien Bellet

Arjun Nitin Bhagoji

Kallista Bonawit

Zachary Charles

Rafael G. L. D'Oliveira

Hubert Eichner

Salim El Rouayheb

Josh Gardner

Zachary Garrett

Adrià Gascón

Badih Ghazi

Phillip B. Gibbons

Marco Gruteser

Zaid Harchaoui

Chaoyang He

Lie He

Zhouyuan Huo

Justin Hsu

Martin Jaggi

Tara Javidi

Gauri Joshi

Mikhail Khodak

Jakub Konecný

Aleksandra Korolova

Farinaz Koushanfar

Sanmi Koyejo

Tancrède Lepoint

Prateek Mittal

Richard Nock

Ayfer Özgür

Rasmus Pagh

Daniel Ramage

Mariana Raykova

Weikang Song

Sebastian U. Stich

Ziteng Sun

Ananda Theertha Suresh

Florian Tramèr

Praneeth Vepakomma

Jianyu Wang

Li Xiong

Felix X. Yu

Sen Zhao

The term Federated Learning was coined as recently as 2016 to describe a machine learning setting where multiple entities collaborate in solving a machine learning problem, under the coordination of a central server or service provider. Each client's raw data is stored locally and not exchanged or transferred; instead, focused updates intended for immediate aggregation are used to achieve the learning objective.Since then, the topic has gathered much interest across many different disciplines and the realization that solving many of these interdisciplinary problems likely requires not just machine learning but techniques from distributed optimization, cryptography, security, differential privacy, fairness, compressed sensing, systems, information theory, statistics, and more.This monograph has contributions from leading experts across the disciplines, who describe the latest state-of-the art from their perspective. These contributions have been carefully curated into a comprehensive treatment that enables the reader to understand the work that has been done and get pointers to where effort is required to solve many of the problems before Federated Learning can become a reality in practical systems.Researchers working in the area of distributed systems will find this monograph an enlightening read that may inspire them to work on the many challenging issues that are outlined. This monograph will get the reader up to speed quickly and easily on what is likely to become an increasingly important topic: Federated Learning.

Advances and Open Problems in Federated Learning

Yu Zhang

Wenyuan Dai

Sinno Jialin Pan

Transfer learning deals with how systems can quickly adapt themselves to new situations, tasks and environments. It gives machine learning systems the ability to leverage auxiliary data and models to help solve target problems when there is only a small amount of data available. This makes such systems more reliable and robust, keeping the machine learning model faced with unforeseeable changes from deviating too much from expected performance. At an enterprise level, transfer learning allows knowledge to be reused so experience gained once can be repeatedly applied to the real world. For example, a pre-trained model that takes account of user privacy can be downloaded and adapted at the edge of a computer network. This self-contained, comprehensive reference text describes the standard algorithms and demonstrates how these are used in different transfer learning paradigms. It offers a solid grounding for newcomers as well as new insights for seasoned researchers and developers.

Transfer Learning

KDD '12: The 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Aug 12, 2012-Aug 16, 2012 Beijing, China. You can view more information about this proceeding and all of ACM�s other published conference proceedings from the ACM Digital Library: http://www.acm.org/dl.

ACM SIGKDD Workshop on Health Informatics

Hi-Kdd'12

Wei Li

Ting Yang

Renewable Energy Microgeneration Systems presents the latest technology advances in small-scale energy generation (electricity and heat) in the context of low/medium voltage level electric power distribution networks. With a focus on scientific innovations of the methodologies, approaches and algorithms in enabling efficient and secure operation of microgeneration systems, this book also analyzes the current understanding of motivations and barriers affecting microgeneration adoption with the aim of identifying opportunities for improving the field deployment. Considering the recent advances of theories and implementations in modeling, design, planning and management of different forms of microgeneration systems, this reference provides applied researchers in the field of electrical engineering and renewable micro generation incredible insights into microgeneration systems technologies and the potential for new technologies and markets. Provides modeling and optimization methods and techniques for micro-generation systems Covers multidisciplinary content, providing an opportunity for different stakeholders in various engineering fields Includes recent research advances in the field, with a focus on real case studies and policy

Customer-led energy transition to make a sustainable world

Renewable Energy Microgeneration Systems

Jian-Min Zhang

Hong Zheng

Yangping Yao

The Second International Symposium on Constitutive Modeling of Geomaterials: Advances and New Applications (IS-Model 2012), is to be held in Beijing, China, during October 15-16, 2012. The symposium is organized by Tsinghua University, the International Association for Computer Methods and Advances in Geomechanics (IACMAG), the Committee of Numerical and Physical Modeling of Rock Mass, Chinese Society for Rock Mechanics and Engineering, and the Committee of Constitutive Relations and Strength Theory, China Institution of Soil Mechanics and Geotechnical Engineering, China Civil Engineering Society. This Symposium follows the first successful International Workshop on Constitutive Modeling held in Hong Kong, which was organized by Prof. JH Yin in 2007. Constitutive modeling of geomaterials has been an active research area for a long period of time. Different approaches have been used in the development of various constitutive models. A number of models have been implemented in the numerical analyses of geotechnical structures. The objective of the symposium is to provide a forum for researchers and engineers working or interested in the area of constitutive modeling to meet together and share new ideas, achievements and experiences through presentations and discussions. Emphasis is placed on recent advances of constitutive modeling and its applications in both theoretic and experimental aspects. Six famous scholars have been invited for the plenary speeches of the symposiums. Some prominent scholars have been invited to organize four specialized workshops on hot topics, including “Time-dependent stress-strain behavior of geomaterials”, “Constitutive modeling within critical state soil mechanics”, “Multiscale and multiphysics in geomaterials”, and “Damage to failure in rock structures”. A total of 49 papers are included in the above topics. In addition, 51 papers are grouped under three topics covering “Behaviour of geomaterials”, “Constitutive model”, and “Applications”. The editors expect that the book can be helpful as a reference to all those in the field of constitutive modeling of geomaterials.

Advances and New Applications

Constitutive Modeling of Geomaterials

Michael Wooldridge

Buenos Aires, Argentina, 25-31 July 2015. ...

Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence

This in-depth tutorial for students, researchers, and developers covers foundations, plus applications ranging from search to multimedia.

Zhiguo Gong

Sheng-Jun Huang

Min-Ling Zhang

Zhi-Hua Zhou

The three-volume set LNAI 11439, 11440, and 11441 constitutes the thoroughly refereed proceedings of the 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2019, held in Macau, China, in April 2019. The 137 full papers presented were carefully reviewed and selected from 542 submissions. The papers present new ideas, original research results, and practical development experiences from all KDD related areas, including data mining, data warehousing, machine learning, artificial intelligence, databases, statistics, knowledge engineering, visualization, decision-making systems, and the emerging applications. They are organized in the following topical sections: classification and supervised learning; text and opinion mining; spatio-temporal and stream data mining; factor and tensor analysis; healthcare, bioinformatics and related topics; clustering and anomaly detection; deep learning models and applications; sequential pattern mining; weakly supervised learning; recommender system; social network and graph mining; data pre-processing and featureselection; representation learning and embedding; mining unstructured and semi-structured data; behavioral data mining; visual data mining; and knowledge graph and interpretable data mining.

23rd Pacific-Asia Conference, PAKDD 2019, Macau, China, April 14-17, 2019, Proceedings

Advances in Knowledge Discovery and Data Mining

The three-volume set LNAI 11439, 11440, and 11441 constitutes the thoroughly refereed proceedings of the 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2019, held in Macau, China, in April 2019. The 137 full papers presented were carefully reviewed and selected from 542 submissions. The papers present new ideas, original research results, and practical development experiences from all KDD related areas, including data mining, data warehousing, machine learning, artificial intelligence, databases, statistics, knowledge engineering, visualization, decision-making systems, and the emerging applications. They are organized in the following topical sections: classification and supervised learning; text and opinion mining; spatio-temporal and stream data mining; factor and tensor analysis; healthcare, bioinformatics and related topics; clustering and anomaly detection; deep learning models and applications; sequential pattern mining; weakly supervised learning; recommender system; social network and graph mining; data pre-processing and feature selection; representation learning and embedding; mining unstructured and semi-structured data; behavioral data mining; visual data mining; and knowledge graph and interpretable data mining.

Charles X. Ling

A Guide to Successful Master's and Phd Degress in Science & Enigineering

Privacy and Incentive

Federated Learning

Qiang Yang

About

Books

Join the club