I-I Reading Group

I-I (iDEA-iSAIL) group is a statistical learning and data mining reading group at UIUC, coordinated by Prof. Hanghang Tong and Prof. Jingrui He. The main purpose of this group is to educate and inform its members of the recent advances of machine learning and data mining.

Regular Meetting.

Time: 9:30 - 11:30 pm.

Zoom: https://illinois.zoom.us/j/3935113249?pwd=WmFONnFJUHlBVlYrdHFPbFlvYndHQT09

Unless otherwise notified, our regular weekly meeting for Fall 2020 is Mon 9:30-11:30 pm via Zoom. If you would like to present in an upcoming meeting, please email dzhou21/lecheng4 [at] illinois [dot] edu or submit a pull request and add to the table!

Schedule for 2021 Summer:

Dates	Presenters	Topics	Materials
Jun 16, 2021	Jun Wu, Lihui Liu	KDD Dry Run
Jun 18, 2021	Yikun Ban, Yao Zhou	KDD Dry Run
Jun 21, 2021	Boxin Du, Si Zhang	KDD Dry Run
Jun 23, 2021	Lihui Liu	KDD Dry Run
Jun 28, 2021	Dawei Zhou	Hunting Faculty Jobs in a Tight Market
July 5, 2021	Yao Zhou, Xu Liu	Industry Job Search
July 12, 2021	Si Zhang, Boxin Du	Hacking Return Offers from Industry Research Labs
July 19, 2021	Shengyu Feng	Graph Optimal Transport
July 26, 2021	Jun Wu	Mixup	Manifold Mixup
Aug 2, 2021	Lecheng Zheng	Transfer Learning
Aug 9, 2021

Schedule for 2021 Spring:

Dates	Presenters	Topics	Materials
Feb 22, 2021	Lecheng Zheng	Contrastive Learning	SupCon,SimCLR, CPC, MOCO
Mar 1, 2021	Wenxuan Bao	Robustness on Federated Learning	Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent
Mar 8, 2021	Jian Kang	Neural Tangent Kernel	Slides
Mar 15, 2021	Yuchen Yan	Positional Embedding and Structural Embedding in Graphs	Position Aware GNN
Mar 22, 2021	Lecheng Zheng,	WWW Dry Run
Mar 29, 2021	Yikun Ban, Haonan Wang	WWW Dry Run
Apr 5, 2021	Qinghai, Baoyu	WWW Dry Run
Apr 12, 2021	Boxin Du	Preliminary Exam Dryrun
Apr 19, 2021	Dongqi Fu	De-Oversmoothing in GNNs	PREDICT THEN PROPAGATE, PAIRNORM
Apr 26, 2021	Yuheng Zhang	Deep Q-learning and Improvements	Rainbow, Deep Q-Network, Slides
May 3, 2021	Shweta Jain	Degree Distribution Approximation	SADDLES
May 10, 2021	Jun Wu	Knowledge Distillation	1, 2, Slides
May 17, 2021	Lihui Liu	Knowledge Graph Embedding	1, 2

Schedule for 2020 Fall:

Dates	Presenters	Topics	Materials
Sept 7, 2020	Max Welling （IAS Talk）	Graph Nets: The Next Generation
Sept 14, 2020	Yikun Ban	Online learning/ Bandits	[Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions] (https://drive.google.com/file/d/1iQtEnTaZ4N_jnJ6y5APwJkDMpUYlrBLR/view?usp=sharing)
Sept 21, 2020	Shengyu Feng	Graph Contrastive Learning	GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training, slides
Sept 28, 2020	Lihui Liu	Neural subgraph counting	Neural subgraph isomorphism counting, slides
Oct 5, 2020	Yao Zhou	Preliminary exam dry run	Preliminary exam dry run
Oct 12, 2020	Jun Wu	Pre-Training	Using Pre-Training Can Improve Model Robustness and Uncertainty, slides
Oct 19, 2020	Ziwei Wu	Sampling Strategy in Graph	Understanding Negative Sampling in Graph Representation Learning
Oct 26, 2020	Dawei Zhou	Preliminary exam dry run	Preliminary exam dry run
Nov 2, 2020	Haonan Wang	GMNN: Graph Markov Neural Networks	GMNN: Graph Markov Neural Networks, slides
Nov 9, 2020	Lecheng Zheng	Self-supervised Learning	Multi-label Contrastive Predictive Coding, slides
Nov 16, 2020	Dongqi Fu	Fair Spectral Clustering	Guarantees for Spectral Clustering with Fairness Constraints
Nov 23, 2020	Zhe Xu	Transferring robustness	Transferring robustness for graph neural network against poisoning attacks, slides
Nov 30, 2020	Si Zhang	Preliminary exam dry run	Preliminary exam dry run
Dec 7, 2020	Qinghai Zhou	Active Learning on Graphs	Graph Policy Network for Transferable Active Learning on Graphs, slides
Dec 14, 2020	Boxin Du	Box Embedding for KBC	BoxE: A Box Embedding Model for Knowledge Base Completion, slides
Dec 15, 2020	Shweta Jain	Counting cliques in real-world graphs	Slides

Schedule for 2020 Spring:

Dates	Presenters	Topics	Materials
Mar 18, 2020	Yuchen Yan	GAN for graphs	GraphGAN, CommunityGAN
Mar 25, 2020	AAAI20	Turing Award Winners Event	Lecture by Geoffrey Hinton, Yann LeCun, Yoshua Bengio
Apr 1, 2020	Jian Kang	Graph Neural Tangent Kernel (GNTK)	Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
Apr 8, 2020	Dawei Zhou, Yao Zhou	Dry run for The Web Conference 2020	-
Apr 15, 2020	Lecheng Zheng	Self supervised Learning	Representation Learning with Contrastive Predictive Coding
Apr 22, 2020	Boxin Du	Multi-level spectral approach for graph embedding	GraphZoom
Apr 29, 2020	Xu Liu	GCN with syntactic and semantic information	SynGCN
May 6, 2020	Qinghai Zhou	Learning Transferable Graph Exploration	paper
May 13, 2020	-	-	-

Recommended Flows

Introduce 1~2 Research Papers:

• 20 mins: Introduction & Background (Motivation examples, literature review)
• 10 min: Problem Description (Give a formal definition of the studied problems)
• 30 min: Brainstorm Discussion (Propose potential approaches based on your knowledge)
• 30 min: Algorithm (Description of the algorithms in the papers)
• 30 min: Critical Discussion (Pros & Cons of your ideas and the existing one)

Survey a Research Topic

• 20 mins: Introduction & Background (Motivation examples, literature review)
• 20 min: Problem/Subproblems Description (Give a formal definition of the studied problems)
• 60 min: Review (High-level discussion of the existing work)
• 20 min: Conclusion & Future Direction

Covered topics/papers in the past:

Generative Deep Learning:

• Martín Arjovsky, Soumith Chintala, Léon Bottou: Wasserstein Generative Adversarial Networks. ICML 2017: 214-223 
• Gulrajani, Faruk Ahmed, Martín Arjovsky, Vincent Dumoulin, Aaron C. Courville: Improved Training of Wasserstein GANs. NIPS 2017: 5767-5777 
• You, Jiaxuan, et al. "Graphrnn: Generating realistic graphs with deep auto-regressive models." arXiv preprint arXiv:1802.08773 (2018). 
• Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, Stephan Günnemann: NetGAN: Generating Graphs via Random Walks. ICML 2018: 609-618 

Robustness:

• Eric Wong, J. Zico Kolter: Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope. ICML 2018: 5283-5292.  

Meta Learning:

• Chelsea Finn, Pieter Abbeel, Sergey Levine: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. ICML 2017: 1126-1135. 

Fairness Learning:

• Tolga Bolukbasi, Kai-Wei Chang, James Y. Zou, Venkatesh Saligrama, Adam Tauman Kalai: Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. NIPS 2016: 4349-4357.  
• Richard S. Zemel, Yu Wu, Kevin Swersky, Toniann Pitassi, Cynthia Dwork: Learning Fair Representations. ICML (3) 2013: 325-333.  

Adversarial Attacks:

• Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, Le Song: Adversarial Attack on Graph Structured Data. ICML 2018: 1123-1132 . 
• Daniel Zügner, Amir Akbarnejad, Stephan Günnemann: Adversarial Attacks on Neural Networks for Graph Data. KDD 2018: 2847-2856. 
• Guanhong Tao, Shiqing Ma, Yingqi Liu, Xiangyu Zhang: Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples. NeurIPS 2018: 7728-7739 

Tracking PageRank vector:

• Andersen, Reid, Fan Chung, and Kevin Lang. "Local graph partitioning using pagerank vectors." 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06). IEEE, 2006. 
• Ohsaka, Naoto, Takanori Maehara, and Ken-ichi Kawarabayashi. "Efficient pagerank tracking in evolving networks." Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2015. 
• Zhang, Hongyang, Peter Lofgren, and Ashish Goel. "Approximate personalized pagerank on dynamic graphs." Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016. 

Click to see what we have covered in each semester