KDD.SG Seminar on Neural Networks

SIGKDD Singapore & SMU School of Information Systems are jointly organizing this seminar featuring two talks on neural network technologies by two distinguished scientists.

Talks

  • “Graph Neural Networks and Applications” by Jie Tang of Tsinghua University
  • “Rep the Set: Neural Networks for Learning Set Representations” by Michalis Vazirgiannis of Ecole Polytechnique

Date: April 25th 2019
Time: 4.00pm to 6.30pm, beginning with light refreshments
Venue: SIS Seminar Rm B1-1, SMU School of Information Systems, 80 Stamford Road, Singapore 178902

RSVP on our Meetup

Talk#1: Graph Neural Networks and Applications

Graph Neural networks (GNNs) and their variants have generalized deep learning methods into non-Euclidean graph data, bringing a substantial improvement on many graph mining tasks. In this talk, I will revisit graph convolutional networks and investigate how to improve their representation capacity. We discover that the performance of GNNs can be significantly improved with several simple and elegant refinements on the neighborhood aggregation and network sampling steps. Importantly, we show that some of the most expressive GNNs, e.g., the graph attention network, can be reformulated as a particular instance of our models. Extensive experiments on different types of graph benchmarks show that our proposed framework can significantly and consistently improve the graph classification accuracy when compared to state-of-the-art baselines.

Speaker

Jie Tang is a Fuphoto_jietangll Professor and the Vice Chair of the Department of Computer Science and Technology at Tsinghua University. His interests include data mining, social networks, knowledge graph, machine learning, and artificial intelligence. He has been visiting scholar at Cornell University, Hong Kong University of Science and Technology, and Southampton University. He has published more than 300 journal/conference papers and holds 20 patents. His papers have been cited by more than 12,000 times. He served as PC Co-Chair of CIKM’16, WSDM’15, Associate General Chair of KDD’18, and Acting Editor-in-Chief of ACM TKDD, Editors of IEEE TKDE/TBD and ACM TIST. He leads the project AMiner.org for academic social network analysis and mining, which has attracted more than 10 million independent IP accesses from 220 countries/regions in the world. He was honored with the UK Royal Society-Newton Advanced Fellowship Award, CCF Young Scientist Award, NSFC for Distinguished Young Scholar, and KDD’18 Service Award.

Talk#2: Rep the Set: Neural Networks for Learning Set Representations

In several domains, data objects can be decomposed into sets of simpler objects. It is then natural to represent each object as the set of its components or parts. Many conventional machine learning algorithms are unable to process this kind of representations, since sets may vary in cardinality and elements lack a meaningful ordering. In this paper, we present a new neural network architecture, called RepSet, that can handle examples that are represented as sets of vectors. The proposed model computes the correspondences between an input set and some hidden sets by solving a series of network flow problems. This representation is then fed to a standard neural network architecture to produce the output. The architecture allows end-to-end gradient-based learning. We demonstrate RepSet on classification tasks, including text categorization, and graph classification, and we show that the proposed neural network achieves performance better or comparable to state-of-the-art algorithms

Speaker

photo_michalisDr.  Vazirgiannis is a Professor at LIX, Ecole Polytechnique in France. He has conducted research in Frauenhofer and Max Planck-MPI (Germany), in INRIA/FUTURS (Paris). He has been a teaching in AUEB (Greece), Ecole Polytechnique, Telecom-Paristech, ENS (France), Tsinghua, Jiaotong Shanghai (China) and in Deusto University (Spain). His current research interests are on deep and machine learning for Graph analysis (including community detection, graph classification, clustering and embeddings, influence maximization), Text mining including Graph of Words, deep learning for word embeddings with applications to web advertising and marketing, event detection and summarization. He has active cooperation with industrial partners in the area of data analytics and machine learning for large scale data repositories in different application domains. He has supervised twenty completed PhD theses. He has published three books and more than a 200 papers in international refereed journals and conferences and received best paper awards in ACM CIKM2013 and IJCAI2018. He has organized large scale conferences in the area of Data Mining and Machine Learning (such as ECML/PKDD) while he participates in the senior PC of AI and ML conferences – such as AAAI and IJCAI, He has received the ERCIM and the Marie Curie EU fellowships, the Rhino-Bird International Academic Expert Award by Tencent and since 2015 he leads the AXA Data Science chair.

 

Taking Stock of Stock Analysis

On 1 April 2019, we saw the power of machine learning techniques in building an automated stock investment system.  A/Prof Carol Hargreaves described a data science approach to identify top stocks, a trading system that not only she built with her expertise but also used by her personally.  We are grateful for the support from the host ING Bank, and for having Annerie Vreugdenhil (Head of Innovation, ING Wholesale Banking) open the event.

Screenshot 2019-04-02 at 10.55.29 AM.png

Agenda for the Evening

2019-04-03 18.20.32.jpg

Hady Lauw (Chapter Chair) outlined the agenda for the evening, as well as introduced the Singapore Chapter of ACM SIGKDD and our activities covering tutorials, seminars, and symposia to contribute to the data science community in Singapore

2019-04-03 18.20.35.jpg

Annerie Vreugdenhil (CIO of ING Wholesale Banking) shared about the innovation activities pursued by ING

 

2019-04-01-18.54.55.jpg

Carol Hargreaves (Associate Professor, NUS) described the broad arc of her approach in using multiple techniques such as PCA, regression and K-means for identifying top stocks

2019-04-01-19.02.20.jpg

Beyond the concepts, Carol showed a live demo of the techniques

2019-04-01-19.23.57-e1554174796670.jpg

The talk was engaging leading to many follow-up questions from the crowd which included domain experts and banking professionals, as well as data science enthusiasts

KDD.SG Seminar organized by SIGKDD Singapore & ING Bank

SIGKDD Singapore & ING Bank are jointly organizing this seminar delivered by A/Prof Carol Hargreaves, Director of the Data Analytics Consulting Centre at the National University of Singapore. The event will be opened by Annerie Vreugdenhil, Head of Innovation, ING Wholesale Banking.

Using Machine Learning Techniques to Identify Top Stocks

April 1st 2019 | 6.00pm to 8.00pm | ING Bank, Spark #12; 1 Wallich Street, Guoco Tower, 078881

Abstract

Interested in what goes into building an automated stock investment system? Using machine learning techniques of both unsupervised and supervised varieties, one can mine troves of data to discover statistical patterns towards identifying top stocks to trade. Demonstrated on a case study, we will see how the learned models perform upon paper trading, comparing the stock portfolio performance to that of the stock market index.

Speaker

photo_carolhargreavesA/Prof Carol Hargreaves is the Director of the Data Analytics Consulting Centre at the National University of Singapore. Prof Hargreaves has a joint position in the Department of Mathematics & the Department of Statistics & Applied Probability. Her role includes providing data analytics advisory & consulting services to industry, designing and teaching data analytics executive training courses for industry professionals, and is a noted keynote conference speaker and moderator.

Prof Hargreaves has a passion for solving business problems using analytics and machine learning techniques to build data driven solutions for growth and effective decision-making. She aims to provide her clients with organic revenue growth, allowing business processes to become smarter and faster while keeping customers engaged.

Prof Hargreaves is an analytics and business intelligence professional with over 30 years analytics experience, with leading roles in the pharmaceutical, healthcare & fast moving consumer goods and education industries. Prof Hargreaves has worked with a variety of leading companies to make businesses more intelligent. These include Pfizer, Novartis, Merck Sharp & Dohme, Nestle, MasterFoods, Goodman Fielder, Foxtel, Aztec (IRI), Cegedim Strategic Data (Quintiles), National Health & Medical Research Council, National University of Singapore.

Date/Time Monday 1 April 2019, beginning with light reception at 6.00pm

Venue ING Bank, Spark @ level 12, 1 Wallich Street, Guoco Tower, 078881

RSVP on our Meetup

See you there!

What Should A Data Scientist Know?

That’s the question that a group of data scientists from industry and academia discussed over dinner on 14 December 2018 at the NUSS Suntec City Guild House.  We were fortunate to have Marianne Winslett, a professor emerita of computer science at the University of Illinois at Urbana–Champaign, to open the event with a keynote address. We see the role of SIGKDD as contributing to identifying and building the skills required for data science professionals.  Though simple and direct answers to such a complex question are elusive, the discussions were fruitful and pointed us in the right direction. It was also a chance for us to reflect and regroup as a community.

IMG_6447.JPG

Marianne Winslett (UIUC) gave her take on the question, including the need for standards to ensure that professionals could build something that’d work, the need for a realistic mindset aware of the limitations of statistics, as well as the attention to ethical issues

IMG_6515.JPG

In between dinner courses, we had breakout discussions on the topic, moderated by Giuseppe Manai (Chapter Secretary)

IMG_6523.JPG

Though it was not by deliberate design, one table had primarily industry professionals, which brought forth issues on how to hire and select the right data scientists

IMG_6525.JPG

The other table just happened to have many academicians, with discussions touching on the skills and competencies of data scientists

IMG_6536.JPG

Hady Lauw (Chapter Chair) closed the event, summarizing the noted points for future follow-ups.

IMG_6592.JPG

A fruitful discussion over a satisfying dinner with a growing community.  From left: Cheng Long (NTU), Aixin Sun (NTU), Yuchen Li (SMU), Serene Ow (Grab), Graham Williams (Microsoft), Joao Gama (DataRobot), Giuseppe Manai (Chapter Secretary, ING FutureLabs Ventures), Xiaoli Li (I2R), Aloysius Lim (Chapter Membership Chair, Eureka AI), Huayu Wu (DBS), Bing Tian Dai (SMU), Jing Jiang (SMU), Marianne Winslett (UIUC), Hady Lauw (Chapter Chair, SMU)

 

 

Networking over Networks

On 18 Sep, we had a chance to learn about the power of networks from Dr. Gábor Benedek (Lynx Analytics), while networking with data science enthusiasts over pizza and beer. We are also grateful to WeWork for hosting our event.  Here are a few pictures to remember by.

kddtutorial3_intro.jpg

Giuseppe Manai (Chapter Secretary) introduced the speaker Gábor Benedek, PhD, who would be speaking about Big Graph Data Intelligence

kddtutorial3_gabor.jpg

In addition to graph theory and techniques, Gábor covered several case studies relating to social and health sciences as well

kddtutorial3_pizza

Networks gave us something to “chew on”, while pizza gave us something to chew while networking

kddtutorial3_wework2.jpg

WeWork provided a conducive space for learning together