Graph Structure of Neural Networks
12. července 2020
Řečníci
Jiaxuan You
Řečník · 2 sledující
Kaiming He
Řečník · 1 sledující
Jure Leskovec
Řečník · 17 sledujících
Saining Xie
Řečník · 0 sledujících
O prezentaci
Neural networks are often represented as graphs of connections between the neurons. However, despite their wide use there is currently no understanding of the relationship between the graph structure of a neural network and its predictive performance. Here we systematically investigate this relationship, via developing a novel graph-based representation of neural networks called relational graph, where computation is specified by rounds of message exchange along the graph structure. Using our novel framework we show that (1) there is a “sweet spot”, where relational graphs within certain range of average path length and clustering coefficient lead to neural networks with significant improvements in predictive performance; (2) perhaps even more surprisingly, we find that these sweet spots tend to highly correlate across different architectures and datasets; and, (3) we show that discovering top-performing relational graphs only requires a few epochs of training. Overall, our results suggest promising avenues for designing and understanding neural networks with graph representations.Neural networks are often represented as graphs of connections between the neurons. However, despite their wide use there is currently no understanding of the relationship between the graph structure of a neural network and its predictive performance. Here we systematically investigate this relationship, via developing a novel graph-based representation of neural networks called relational graph, where computation is specified by rounds of message exchange along the graph structure. Using our no…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
Matematika
Kategorie · 2,4k prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Multi-Agent Routing Value Iteration Network (MARVIN)
Zhlédnout později
New Oracle-Efficient Algorithms for Private Synthetic Data Release
Zhlédnout později
MTL2L: A Context Aware Neural Optimiser
Zhlédnout později
Q&A session #1
Zhlédnout později
