The workshop will bring together leaders from academia and industry to showcase recent advances in Machine Learning and AI in Relational domains, Foundation Models, and Multimodal AI. The workshop will discuss methodological advancements, a wide range of applications to different domains, machine learning frameworks and practical challenges for large-scale training and deployment of AI models.
Registration
The Stanford Graph Learning Workshop will be held on Tuesday, Oct 24 2023, 09:00 - 18:00 Pacific Time.
The event will take place at Stanford University and will be live-streamed online. Free registrations are available. Register here.
Schedule
| 08:00 - 09:00 | Registration & Breakfast | ||
|---|---|---|---|
| 09:00 - 09:10 | Jure Leskovec, Stanford University | Welcome and Overview [ Slide ][ Video ] | |
| 09:10 - 09:40 | Matthias Fey, PyG & Kumo.AI | What’s New in PyG, Torch Frame [ Slide ][ Video ] | |
| 09:40 - 10:00 | Serina Chang, Stanford University & Qi Xiu, Hitachi | Machine Learning for Supply Chain Management [ Slide ][ Video ] | |
| 10:00 - 10:20 | Michi Yasunaga, Stanford University | Retrieving from Knowledge Bases for Large Language Models [ Slide ][ Video ] | |
| 10:20 - 10:40 | Weihua Hu, Kumo.AI | Graph Neural Networks for Declarative ML [ Slide ][ Video ] | |
| 10:40 - 11:00 | Break | ||
| 11:00 - 11:20 | Joshua Robinson, Stanford University | Next Generation Architectures for Graph ML [ Slide ][ Video ] | |
| 11:20 - 11:40 | Qian Huang, Stanford University | Large Language Models As AI Research Agents [ Slide ][ Video ] | |
| 11:40 - 12:00 | Yusuf Roohani, Stanford University | From cell engineering to drug discovery: Predicting outcomes of multi-gene cell perturbations [ Slide ][ Video ] | |
| 12:00 - 12:20 | Ravi Motwani & Michael Galkin, Intel Labs | Towards Graph Foundation models and distributed training of GNNs [ Slide ][ Video ] | |
| 12:20 - 12:30 | Joseph Huang, Stanford University | Stanford Data Science Institute affiliates program [ Video ] | |
| 12:30 - 13:30 | Lunch | ||
| 13:30 - 13:50 | Mahashweta Das, VISA | Graph ML on Financial Data[ Video ] | |
| 13:50 - 14:10 | Karthik Subbian, Amazon | Graph Representation Learning at Amazon [ Slide ][ Video ] | |
| 14:10 - 15:00 | Moderator: Hema Raghavan (Kumo.AI) Panelists: |
Industry Panel – Challenges and Opportunities for Graph Learning [ Video ] | |
| 15:00 - 15:20 | Hamed Nilforoshan, Stanford University | Zero-shot causal learning [ Slide ][ Video ] | |
| 15:20 - 15:40 | Minkai Xu, Stanford University | Generative Modeling for Drug Discovery [ Slide ][ Video ] | |
| 15:40 - 16:00 | Rishi Puri & Mohammad Nabian, NVIDIA | PyG and Modulus: An open-source framework for building, training, and fine-tuning Physics-ML models [ Slide ][ Video ] | |
| 16:00 - 16:15 | Poster slam [ Slide ][ Video ] | ||
| 16:15 - 18:00 | Happy Hour & Poster Session | ||
Posters
- Kumo: Declarative ML platform for relational databases - Viman Deb & Vid Kocijan
- Uncertainty Quantification over Graph with Conformalized Graph Neural Networks - Kexin Huang
- Graph Neural Networks for supply chains - Serina Chang, Zhiyin Lin, Benjamin Yan
- PRODIGY: Enabling In-context Learning Over Graphs - Qian Huang
- Learning Large Graph Property Prediction via Graph Segment Training - Kaidi Cao
- Zero-shot causal learning - Hamed Nilforoshan
- Med-Flamingo: a Multimodal Medical Few-shot Learner - Michael Moor
- Neural Networks for Eigenvector Data - Joshua Robinson
- Graphs in Biomedicine: Advancing Precision Medicine - Yusuf Roohani
- Evaluating Self-Supervised Learning for Molecular Graph Embeddings - Hanchen Wang
- Graph and Geometric Generative Models for Drug Discovery - Minkai Xu
- RA-CM3: Retrieval-Augmented Multimodal Language Modeling - Michihiro Yasunaga
- Learning Reduced-Order Models for Cardiovascular Simulations using Graph Neural Networks - Luca Pegolotti
- GNN Application on Key Information Extraction in Document AI - Fuheng Wu
- Open MatSci ML Toolkit: Graph Learning for Materials Science - Santiago Miret
- Solutions and challenges to optimize a cellular network with Graph Neural Networks - Oscar Llorente Gonzalez
- RL4CO: A Unified Reinforcement Learning For Combinatorial Optimization Libarary - Junyoung Park
- ChemReasoner: Large Language Model-driven Search over Chemical Spaces with Quantum Chemistry-guided Feedback - Sutanay Choudhury/Henry Sprueill
- GraphLearn-for-Pytorch: GPU-accelerated Distributed GNN Training on PyTorch & Li Su
- Enhanced Semantic Representation Learning through Integration of Behavioural and Content Data - Mohammed Danish Kalim/Mohit Agarwal
- Abuse Detection in Online B2C Marketplace using Heterogeneous Graph with Multidimensional Edge Features - Rajesh Kumar SA
- Semantic Link Prediction for Real-Time Document Understanding in Production - Alec Stashevsky
- Temporal Graph Benchmark for Machine Learning on Temporal Graphs - Shenyang(Andy) Huang
- Generating Embedding through BERT and graph_based method - Chao Gan
- PyG and Modulus: An open-source framework for building, training, and fine-tuning Physics-ML models - Mohammed Nabian