This repo is based on the KDD 2020 official website, to summarize the following aspects, for myself and everyone to quickly get the whole idea of this conference.
- the key words of accepted papers
- the topic of accepted papers
- author information of accepted papers
- KDD awards
- KDD workshop, tutorial
- summary
- Keyword cloud
- Topic cloud
- KDD awards
- workshop and tutorial, papers
- Total num (RT+ADS), Research Track, and Applied Data Science (ADS) track of paper in KDD 2020 is : **338 217 121 **;
- Total number of submission: 2035 (the highest in history,over 13% more than the second highest one)
- Research track(long paper): 1279 submition, 216 accepted, 216 / 1279 = 16.9%;
- Conference schedule: Click here
- KDD recent 7 years submission and recept data:
[2012-ACM SIGKDD 数据挖掘及知识发现会议]
An introduction about the history of KDD, the topic of KDD, and the general issue about the 2012 KDD conference to be held in Beijing, China, by Prof. Jiangyong Wang from Tsinghua University.
| topic | num_papers |
|---|---|
| graph | 74 |
| convolutional neural networks | 6 |
| unsupervised | 6 |
| generative adversarial | 6 |
| reinforcement learning | 6 |
| time series | 5 |
| semi-supervised | 5 |
| real-time | 5 |
| GAN | 4 |
| GNN | 4 |
| multi-task | 4 |
| GCN | 3 |
| meta-learning | 3 |
| Federated | 2 |
| privacy | 2 |
| private | 1 |
| interpretability | 1 |
| Knowledge Distillation | 1 |
| co-training | 1 |
| CNN | 1 |
| GANs | 1 |
| transfer learning | 1 |
Dissertation Award Running Up: Jingbo Shang, Assistant professor in UCSD, PHD from UIUC with Prof.Jiawei Han;
In the speech, Prof.Shang introduced his work during PhD study about automatic learning from text: turning unstructured data into structured knowledge;
QA:
1)How to improve our research taste? How to choose a good topic?
I focused on three parts: real problem; real data; real solution.
**If an algorithm is very specific, if we release some condition, the method will not work that well. So we have the chance to improve.**For example, for my PHD study, supervised learning on text is well studied, but i move to unsupervised learning, to form my phd thesis.
2)What is your future research interest?
two things,
- week supervision. Utilize huge amount of unlabelled data;
- How to combine sturctured and unstructured data;
Dissertation Award: Rediet Abebe, Assistant Professor in UC Berkeley, PHD from Cornell University;
"Get Another Label? Improving Data Quality And Data Mining Using Multiple, Noisy Labelers."
Victor S. Sheng, Foster Provost and Panagiotis Ipeirotis
"ArnetMiner: Extraction And Mining Of Academic Social Networks."
Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang and Zhong Su
Mike Zeller, Head of AI strategy and solutions , Temask.
Research Track
Best Paper Award On Sampled Metrics for Item Recommendation Walid Krichene: Google; Steffen Rendle: Google
Best Paper Runner-up Malicious Attacks against Deep Reinforcement Learning Interpretations Mengdi Huai: University of Virginia; Jianhui Sun: University of Virginia; Renqin Cai: University of Virginia; Liuyi Yao: University of New York at Buffalo; Aidong Zhang: University of Virginia
Best Student Paper Award TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations Ang Li: Duke University; Yixiao Duan: Beihang University; Huanrui Yang: Duke University; Yiran Chen: Duke University; Jianlei Yang: Beihang University
Applied Data Science Track
Best Paper Award
Temporal-Contextual Recommendation in Real-Time Yifei Ma; Murali Balakrishnan Narayanaswamy, Haibin Lin and Hao Ding from Amazon.
Presenter: Han Xu, Yaxin Li, Wei Jin, Jiliang Tang, from Michigan State University
paper list:
- Salary Prediction Problem as Ordinal Regression, Speaker: Tomoki Ohtsuki
- Dynamic Non-negative Matrix Factorization with Temporal Smoothness and Its Application to Email Analysis, Speaker: Mandar Chaudhary
- Large-Scale Talent Flow Embedding for Company Competitive Analysis, Speaker: Le Zhang
- Fine-grained Job Salary Benchmarking with Nonparametric Dirichlet-process-based Latent Factor Model, Speaker: Qinxin Meng
- Personalized Employee Tranining Course Recommendation with Career Development Awareness, Speaker: Chao Wang
- Research on Medical Talent Evaluation through Applied Behavior Analysis, Speaker: Bo Jin
topics:
- - Talent behavior modeling
- - Talent personality and leadership
- - Talent performance assessment
- - Talent recruitment
- - Talent retention and incentive
- - Talent email sentiment analysis
- - Job recommendation
- - Fairness on recruitment
- - Skill recommendation
- - Person-job fit and job satisfaction
- - Career development
- - Professional social networks
- - Team formation and task assignment
- - Group-based decision-making
- - Organizational change and stability
- - Organizational culture and communication
- - Organizational competition analysis
- - Strategic management and planning
topics:
1)Novel Deep Learning Techniques for Spatial and Spatio-Temporal Data: Spatial representation learning and deep neural networks for spatio-temporal data and geometric data Interpretable deep learning for spatial-temporal data Deep generative models for spatio-temporal data Deep reinforcement learning for spatio-temporal decision making problems
2)Novel Applications of Deep Learning Techniques to Spatio-temporal Computing Problems. : Geo-imagery and point cloud analysis (for remote sensing, Earth science, etc.) Deep learning for mobility and traffic data analytics Location-based social network data analytics, spatial event prediction and forecasting Learning for biological data with spatial structures (bio-molecule, brain networks, etc.)
3)Novel Deep Learning Systems for Spatio-temporal Applications: Real-time decision-making systems for traffic management, crime prediction, accident risk analysis, etc. GIS systems using deep learning (e.g., mapping, routing, or Smart city) Mobile computing systems using deep learning Interpretable deep learning systems for spatio-temporal temporal data
paper list:
-
1.Modeling Spatiotemporal Geographic-Semantic Dynamics for Urban Hotspots Prediction, by Guangyin Jin, Hengyu Sha, Yanghe Feng, Cheng Qing and Huang Jincai.
-
2.Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow, by Thomas Vandal and Ramakrishna Nemani.
-
3.Fusion Recurrent Neural Network, by Yiwen Sun, Yulu Wang, Kun Fu, Zheng Wang, Changshui Zhang and Jieping Ye.
-
4.DeepSampling: Selectivity Estimation with Predicted Error and Response Time, by Tin Vu and Ahmed Eldawy.
-
5.Generate Street Map Images from Satellite Images and Crowd-sourced Geographic data using GAN, by Ying Zhang, Yifang Yin, Roger Zimmermann, Guanfeng Wang and Jagannadan Varadarajan.
-
6.Transformer Hawkes Process , bySimiao Zuo, Haoming Jiang, Zichong Li, Tuo Zhao and Hongyuan Zha.
-
7.Towards Spatial Variability Aware Deep Neural Networks (SVANN): A Summary of Results , by Jayant Gupta, Yiqun Xie and Shashi Shekhar.
-
8.Deep Multi-Sensor Domain Adaptation on Active and Passive Satellite Remote Sensing Data , byXin Huang, Sahara Ali, Sanjay Purushotham, Jianwu Wang, Chenxi Wang and Zhibo Zhang.
paper list:
- CICLAD: A Fast and Memory-efficient Closed Itemset Miner for Streams
- Parameterized Correlation Clustering in Hypergraphs and Bipartite Graphs
- A Non-Iterative Quantile Change Detection Method in Mixture Model with Heavy-Tailed Components
- Learning Based Distributed Tracking
- Stable Learning via Differentiated Variable Decorrelation
These 5 papers with one sentence summary:
[CICLAD: A Fast and Memory-efficient Closed Itemset Miner for Streams]
2020 KDD, Tomas Martin, Guy Francoeur, Petko Valtchev from Centre de recherche en intelligence artificielle (CRIA), UQÀM, Canada;
summary: This paper proposes a new intersection-based sliding-window (frequent closed itemset )FCI miner, to mine the association rules.
[Parameterized Correlation Clustering in Hypergraphs and Bipartite Graphs]
2020 KDD, Nate Veldt (Cornell University), Anthony Wirth (U of Melbourne), David F. Gleich (Purdue);
summary: This paper solves clustering problem in Hypergraphs and Bipartite Graphs.
[A Non-Iterative Quantile Change Detection Method in Mixture Model with Heavy-Tailed Components]
2020 KDD,Yuantong Li from Purdue, Qi Ma and Sujit K. Ghosh from North Carolina State University;
summary: This is a proof-of-concept paper. This paper proposes a data-driven method for parameter estimation in mixture models with heavy-tailed component. While traditionally, most litereatures use iterative Expectation Maximization (EM) method, this paper proposes Non-Iterative Quantile Change Detection (NIQCD) by using change-point detection methods.
[Learning based distributed tracking]
2020 KDD, Hao Wu, Junhao Gan, Rui Zhang from U of Melbourne;
summary: This paper studies the fundamental problem called Distributed Tracking. WIth the popularity of machine learning, people starts to explore the theory of ML via data distribution. This paper follows this line of research and proposes two methods, i.e., w and w/o known of data distribution in advance, to minimize the communication cost in coordinator and players.
[Stable Learning via Differentiated Variable Decorrelation]
2020 KDD, Zheyean Shen: Tsinghua University; Peng Cui: Tsinghua University; Jiashuo Liu: Tsinghua University; Tong Zhang: Hong Kong University of Science and Technology; Bo Li: Tsinghua University; Zhitang Chen: Huawei Noah's Ark Lab
summary: This paper studies model robustness, i.e., the model could achieve similar performance in the chaning wild environment.
Method: This paper incorporates the unlabelled data from multiple environment in the variable decorrelation framework.
Topics of Interest:
Topics of interest include, but not limited to, the following aspects :
- Data mining for urban planning and city configuration evaluation
- Mining urban environmental, pollution, and ecological data
- Knowledge discovery from sensor data for saving energy and resources
- Data mining for sustainable and intelligent cities
- Urban sensing and city dynamics sensing
- Knowledge fusion from data across different domains
- City-wide traffic modeling, visualization, analysis, and prediction
- City-wide human mobility modeling, visualization, and understanding
- City-wide intelligent transportation systems
- Anomaly detection and event discovery in urban areas
- Mining urban economics
- Social behavior modeling, understanding, and patterns mining in urban spaces
- City-wide mobile social applications in urban areas
- Location-based social networks enabling urban computing scenarios
- Smart recommendations in urban spaces
- Intelligent delivery services and logistics industries in cities
- Mining data from the Internet of Things in urban areas
- Managing urban big data on the cloud
- Interactive visual data analytics for urban computing
- Federated learning for urban computing
Accepted papers:
-
Towards Dynamic Urban Bike Usage Prediction for Station Network Reconfiguration [***PDF]*** Xi Yang and Suining He (The University of Connecticut)
-
Leveraging Change Point Detection for Activity Transition Mining in the Context of Environmental Crowdsensing [***PDF]*** Hafsa El Hafyani(UVSQ-Université Paris-Saclay), Karine Zeitouni(UVSQ-Université Paris-Saclay), Yehia Taher(UVSQ-Université Paris-Saclay), Mohammad Abboud(Lebanese University)
-
The Anatomy of the Daily Usage of Bike Sharing Systems: Elevation, Distance and Seasonality [***PDF]*** Injung Kim(University of Pittsburgh), Konstantinos Pelechrinis(University of Pittsburgh), Adam J. Lee(University of Pittsburgh)
-
A Distributed Travel Time Estimation Capability for Metropolitan-sized Road Transportation Networks [***PDF]*** AArif Khan(Pacific Northwest National Laboratory), Arun V Sathanur(Pacific Northwest National Laboratory), Kelsey Maass(University of Washington), Robert Rallo(Pacific Northwest National Laboratory)
-
An Interactive Data Visualization and Analytics Tool to Evaluate Mobility and Sociability Trends During COVID-19 [***PDF]*** Fan Zuo(New York University), Jingxing Wang(University of Washington), Jingqin Gao(New York University), Kaan Ozbay(New York University), Xuegang Jeff Ban(University of Washington), Yubin Shen(New York University), Hong Yang(Old Dominion University), Shri Iyer(New York University)
-
Trends Drift Discovery for Individual Highway Drivers through Ensemble Learning [***PDF]*** Weilong Ding(North China University of Technology), Zhe Wang(North China University of Technology), Jianwu Wang(University of Maryland), and Yanbo Han(North China University of Technology)
-
Cross-Domain Customer Profiling: Mining Passengers’ Food Ordering Patterns From Transportation Habits [***PDF]*** Xueou Wang(National University of Singapore), Yifang Yin(National University of Singapore), Bryan Hooi(National University of Singapore), See Kiong Ng(National University of Singapore), Wynne Hsu(National University of Singapore), Renrong Weng(Grab), Xiang Hui Nicholas Lim(Grab), Rui Tan(Grab)
-
Speed Anomalies and Safe Departure Times from Uber Movement Data [***PDF]*** Nabil Al Nahin Ch(University of New Hampshire), John Krumm(Microsoft Research), Andrew Kun(University of New Hampshire)
-
Bus Fuel Consumption Problem: An in-depth Analysis and Prediction [***PDF]*** Thanh-Nam Doan, Le Tuan Phan, Mina Sartipi. (University of Tennessee at Chattanooga)
-
Online Weighted Bipartite Matching with Capacity Constraints [***PDF]*** Hao Wang, Zhenzhen Yan, Xiaohui Bei. (Nanyang Technological University)
-
TESLA: A Centralized Taxi Dispatching Approach to Optimizing Revenue Efficiency with Global Fairness [***PDF]*** Huigui Rong(Hunan University), Qun Zhang(Hunan University), Xun Zhou(University of Iowa), Hongbo Jiang(Hunan University), Da Cao(Hunan University), Keqin Li(SUNY New Platz).
-
RAD: Rapid Automobile Data Analytics Framework for Structured Data [***PDF]*** Nikhil Muralidhar(Virginia Polytechnic Institute and State University), Brian Mayer(Virginia Polytechnic Institute and State University), Nathan Self(Virginia Polytechnic Institute and State University), Naren Ramakrishnan(Virginia Polytechnic Institute and State University), Panduranga Kondoju(Ford Motor Company), Basavaraj Tonshal(Ford Motor Company), John Schmotzer(Ford Motor Company)