On 24 October 2019, in collaboration with Singapore OpenMined, we feature two speakers in our KDD.SG Seminar series, this time hosted at SMU School of Information Systems.

The first talk on data privacy in machine learning was given by Assistant Professor Reza Shokri, who is NUS Presidential Young Professor.

The second talk on tests and metrics to evaluate machine learning model explanations was given by Naresh Rajendra Shah, who is Co-founder and CTO at Untangle AI.

We thank both speakers as well as OpenMined for what turned out to be a mind-opening experience for all the attendees.

On 29 May 2019, we featured Michael Tsang as a speaker in our KDD.SG Seminar series, this time hosted at WeWork 71 Robinson. In his talk, Michael discussed  industry trends on  hybrid multi-cloud as well as its business implications and technology impact.  Here are several moments captured in photos.

Rise of Hybrid Multi-cloud, irrelevant buzzword or important trend?

May 29, 2019 | 6pm to 8.30pm | WeWork 71 Robinson

Abstract

Cloud Computing has become a mainstay of IT industry in recent years. Many variations and flavors had since developed, and they can be quite confusing to those who are unfamiliar. Many chose to follow suit simply because it is a growing trend, but they may not be making the most appropriate decisions for their businesses if the intricacies aren’t studied thoroughly.

Cloud Computing in general can be viewed as a 3 layer architecture where, IaaS (infrastructure as a service) sits at the bottom, PaaS (platform aaS) in the middle, and SaaS (software aaS) on top.

Being the foundation layer, IaaS is critical in dictating an efficient and effective infrastructure that powers today’s businesses. In order to provision, deploy, and manage IaaS appropriately, specific terminology was developed to illustrate some of the most common deployment models, including private cloud, public cloud, hybrid cloud, and multi-cloud.

While public cloud, private cloud, and even hybrid cloud have been popularized, business needs continue to evolve and technology continue to advance. Today, Hybrid multi-cloud is becoming a growing trend in cloud computing. Deploying a cloud infrastructure that combines private on-premise data centers and multiple public cloud providers (hybrid multi-cloud) is daunting, but businesses continue to flock to this model. In his talk, Michael will discuss current industry trends and consumptions surrounding hybrid multi-cloud, implications of business and technology impact, and illustrate through a use case the need to embrace what is to come.

Speaker

Michael Tsang currently serves as Senior Director of Channel Management APAC at Equinix, the leading data center provider in the world.

Prior to joining Equinix, Michael led engineering and research efforts at Hulu for 1 year, in areas such as recommendation, prediction, and pattern recognition.

Before Hulu, Michael spent 3.5 years with Alibaba, responsible for driving market entry and business growth in North and South America regions. He also led and completed Alibaba Cloud’s European data center strategy and owned Hong Kong’s partner management.

Prior to that Michael was with Microsoft for 16 years in various engineering roles including development and testing; gaining experience in operating systems, business rule engines, video rendering and transcoding, online advertising, and big data stream computing. Prior to Microsoft, he served at Hewlett-Packard in LaserJet and network management products.

Date/Time Wednesday 29 May 2019, beginning with a light reception at 6pm

Venue WeWork 71 Robinson Road Singapore 068895

RSVP on our Meetup.

See you there!

On 25 April 2019, we were honored to feature two speakers in our KDD.SG Seminar series and host them in SMU School of Information Systems.

Prof Jie Tang from Tsinghua University summarized several works on using deep learning for deriving graph representations, distilled their fundamental concepts, and described several generalizations and extensions on such models.

In turn, Prof Michalis Vazirgiannis from Ecole Polytechnique described his recent work on using deep learning to derive representations for sets.

The audience was engaged, and the ensuing questions-and-answers were lively with a number of relevant questions. Overall, it was a very informative and inspiring session that certainly amplified our understanding of deep learning and 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 Full 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

Dr.  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.