On the 27th October 2023, the Institute for Data Science and AI Seminar Series (IDSAI) welcomed Petar Veličković, Staff Research Scientist at Google Deep Mind and Affiliated Lectureship at the University of Cambridge, to give a presentation titled ‘Decoupling the Input and the Computational Graph: The Most Important Unsolved Problem in Graph Representation.’
Abstract:
When deploying graph neural networks, we often make a seemingly innocent assumption: that the input graph we are given is the ground-truth. However, as my talk will unpack, this is often not the case: even when the graphs are perfectly correct, they may be severely suboptimal for completing the task at hand. This will introduce us to a rich and vibrant area of graph rewiring, which is experiencing a renaissance in recent times. I will discuss some of the most representative works, including two of our own contributions (arxiv.org/abs/..., arxiv.org/abs/..., one of which won the Best Paper Award at the Graph Learning Frontiers Workshop at NeurIPS'22.
Speaker Bio:
Petar Veličković is a Research Scientist at DeepMind. He holds a PhD degree from the University of Cambridge (obtained under the supervision of Pietro Liò), with prior collaborations at Nokia Bell Labs and Mila. His current research interests broadly involve devising neural network architectures that operate on nontrivially structured data (such as graphs), and their applications in algorithmic reasoning and computational biology.
Petar has published his work in these areas at both machine learning venues (ICLR, NeurIPS-W, ICML-W) and biomedical venues and journals (Bioinformatics, PLOS One, JCB, PervasiveHealth). In particular, he is the first author of Graph Attention Networks, a popular convolutional layer for graphs, and Deep Graph Infomax, a scalable local/global unsupervised learning pipeline for graphs. His research has been featured in media outlets such as ZDNet. Additionally, he has co-organised workshops on Graph Representation Learning at ICLR 2019 and NeurIPS 2019.
IDSAI:
Manchester’s Institute for Data Science & Artificial Intelligence acts as an access point to the University’s expertise in data science and artificial intelligence, facilitates interactions between researchers and problem holders, owns the University’s data science strategy, and delivers sustainable support for the community.
IDSAI is a key theme within the University’s Digital Futures platform. Digital Futures is a highly interdisciplinary network that operates across the whole range of the University’s digital research, which aims to present a coherent overview of our digital research activity to external stakeholders and bring together our research communities to explore new research areas and address strategic opportunities.
Негізгі бет Decoupling the Input and the Computational Graph - Petar Veličković - IDSAI Seminar Series
Пікірлер