Paper Reading Groups

Spring 2024 Schedule

Spring 2024 Schedule
Week Topic Presenter Reading Materials Slide Link Youtube Link
1 User Personalization for Conversational Dialogue Roshni Iyer Slides
2 Visual generation Zongyu Lin
3 Hypothesis Generation with Large Language Models Chenchen Ye
Slides
4 Multimodal frameworks for text + molecule Mingyu Ma
Slides
5 Knowledge-Graph Augmented Reasoning for LLMs Arvind Vepa
6 Function Vectors in Large Language Models in our reading group Yuanzhou Chen
Slides
7 Segment Anything Anthony Cuturrufo

Winter 2024 Schedule

Winter 2024 Schedule
Week Topic Presenter Reading Materials Slide Link Youtube Link
1 Towards End-to-end Data Pipeline for Effective Data Science Guest Speaker: Jin Wang
2 Learning Generative Models from a Control Perspective for Scientific Discovery Guest Speaker: Dinghuai Zhang
4 Autonomous Chemistry Research with Large Language Models Yanqiao Zhu
Slides
5 Explain AI Models by Locating and Editing Knowledge Shichang Zhang
Slides
6 Knowledge-centric Machine Learning on Graphs Guest Speaker: Yijun Tian
7 Dynamics of Numerical Optimization Yanna Ding
Slides

Fall 2023 Schedule

Fall 2023 Schedule
Week Topic Presenter Reading Materials Slide Link Youtube Link
1 Time-Reversal Latent Graphode for Multi-Agent Dynamical Systems Wanjia Zhao
Slides
2 Recent Trends of Alignment of Large Language Models Zongyu Lin
3 Advancing Healthcare with Multimodal Structural Knowledge Guest Speaker: Hejie Cui
4 When does Graph Neural Network work and when not? Guest Speaker: Haitao Mao
5 Design Space Exploration of High-Level Synthesis Weikai Li Slides

Fall 2022 Schedule

Fall 2022 Schedule
Date Topic Presenter Reading Materials Slide Link Youtube Link
10/4 Session Based Recommendation with GNN Zongyue Qin Slides
10/11 Graph Rewiring Fred Xu
10/18 Graph Diffusion Generative Model Zijie Huang GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation Slides
10/25 Theory of Graph Neural Networks Yanqiao Zhu Theory of Graph Neural Networks: Representation and Learning
11/1 Recent Progress in Explaining GNNs Shichang Zhang 1. Towards Multi-Grained Explainability for Graph Neural Networks 2. Task-Agnostic Graph Explanations Slides
11/8 Graph Oversmoothing JeeHyun Hwang 1. Differentiable Physics informed Graph Networks 2. Grand: Graph Neural Diffusion 3. Pde-gcn: Novel architectures for graph neural networks motivated by partial differential equations 4. Graph Neural Networks as Gradient Flows
11/15 Reasoning of Large Language Model Ziniu Hu 1. Chain of Thought Prompting Elicits Reasoning in Large Language Models 2. Self-Consistency Improves Chain of Thought Reasoning in Language Models 3. Least-to-Most Prompting Enables Complex Reasoning in Large Language Models" 4. Rationale-Augmented Ensembles in Language Models 5. On the Advance of Making Language Models Better Reasoners 6. STaR: Bootstrapping Reasoning With Reasoning
11/22 How People Affect Each Other on Social Networks? Zhiping Xiao Slides

Spring 2022 Schedule

Spring 2022 Schedule
Date Topic Presenter Reading Materials Slide Link Youtube Link
4/5 Static & Dynamic Causal Structural Learning Fred Xu
  • NO-TEAR (2018) & DAG-GNN (2019)
  • CausalVAE (2020)
  • Neural Relational Inference (2018) & Causal Discovery from Videos (2020)
Drive
4/12 Neural Networks as Graphs Derek Xu
  • Graph Structure of Neural Networks (ICML2020)
  • RGP: Neural Network Pruning through Its Regular Graph Structure (arxiv2021)
  • Does unsupervised architecture representation learning help neural architecture search? (NeurIPS2020)
4/19 The lottery ticket hypothesis on GNNs Shichang Zhang Drive
5/3 Recent Advances in Graph Decoders Roshni
  • Graph Auto-Encoder via Neighborhood Wasserstein Reconstruction (ICLR 2022)
  • Variational graph auto-encoders (2016)
  • Graph contrastive learning with augmentations (NeurIPS 2020)
  • Contrastive multi-view representation learning on graphs (PMLR 2020)
  • Top-N: Equivariant Set and Graph Generation without Exchangeability (ICLR 2022)
  • Graph convolutional policy network for goal-directed molecular graph generation (NeurIPS 2018)
  • E(n) equivariant normalizing flows (NeurIPS 2021)
Drive
5/10 Learning P(Y|do(X)) instead of P(Y|X) Song Jiang
  • Causal transportability for neural representations
Drive

Winter 2022 Schedule

Winter 2022 Schedule
Date Topic Presenter Reading Materials Slide Link Youtube Link
1/11 Kewei Cheng
1/18 Message Passing Arjun Subramonian NeurIPS slides
1/25 Zongyue Qin
2/1 Roshni Iyer
  • HyperExpan (EMNLP'21)
  • M^2GNN (WWW'21)
Drive
2/8 Ziniu Hu
2/15 Geometric Deep Learning and Symmetry Fred Xu
2/15 Political Belief Polarity Zhiping (Patricia) Xiao See Slides Slide

Fall 2021 Schedule

Fall 2021 Schedule
Date Topic Presenter Reading Materials Slide Link Youtube Link
9/28 Knowledge Reasoning & Prompting Ziniu Hu
  • 1) LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs
  • 2) Making Pre-trained Language Models Better Few-shot Learners
 Drive
10/12 Algorithm Execution via Graph Representation Learning Zhiping Xiao
  • Neural Execution of Graph Algorithms
  • Pointer Graph Networks
 File
10/19 AlphaFold v2 and EvoFormer Junheng Hao AlphaFold2: Highly accurate protein structure prediction with AlphaFold Doc
10/26 Theory of GNN Derek Xu How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
11/2 GNN Explainability Shichang Zhang On Explainability of Graph Neural Networks via Subgraph Explorations (SubgraphX) Slide 1, Slide 2
11/9 AutoML on graphs Yewen Wang
11/16 Reinforcement Leanring Exploration Yunsheng Bai See Slides Doc
11/23 Causal representation Learning Jiang Song Towards Causal Representation Learning Doc
11/30 Equivariant GNN Zijie Huang See Slides Drive

Spring 2021 Schedule

Spring 2021 Schedule
Date Topic Presenter Reading Materials Slide Link Youtube Link
4/20 Graph Structural Learning Zijie Huang Drive
4/27 Open Domain Question Answering Ziniu Hu
5/4 Inductive Link Prediction Kewei Cheng
5/11 Dyalic Fairness Arjun Subramonian On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections
5/18 GNN & Non-Euclidean Machine Learning Yewen Wang
5/25 Zongyue Qin
6/1 Roshni Iyer