Principal Neighbourhood Aggregation for Graph Nets | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=c00GuCe62mk


Duration: 1:02:18
1,089 views
47

------------------
Join our machine learning product challenge and win 💰cash prizes💰 up to $3,000 : https://ai.science/challenges.
------------------

Speaker(s): Petar Veličković
Facilitator(s): Nabila Abraham

Find the recording, slides, and more info at https://ai.science/e/pna-principal-neighbourhood-aggregation-for-graph-nets--hFAIyD8Zcf196lh8gP0M

Motivation / Abstract

Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on isomorphism tasks and countable feature spaces. In this work, the authors focus on a theoretically motivated aggregation function that includes continuous feature spaces. The authors propose Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degree-scalers (which generalize the sum aggregator). They compare the capacity of different models to capture and exploit the graph structure via a novel benchmark containing multiple tasks taken from classical graph theory, alongside existing benchmarks from real-world domains, all of which demonstrate the strength of their model. This work sheds some light on new aggregation methods which are essential in the search for powerful and robust models.

What was discussed?
- Limitations of single aggregator functions for various neighbourhood sizes and feature distributions
- The best type of aggregator (hint: the answer is none.)
- Optimally expressive GNNs
- Training multi-task GNNs


------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2020-09-16Defining your AI Value Model for Product Success (and Profit) | AISC
2020-09-15Real-World Quantum Communication: One Module at a Time | AISC
2020-09-15Predicting and Understanding Human Choices using PCMC-Net with an application to Airline Itineraries
2020-09-14Product Ideation: From a Hunch to a Concrete Idea
2020-09-14RadioAssistant - Ranking Radiology Patients using Deep Learning | Workshop Capstone
2020-09-11Building a better climate model with Machine Learning | AISC
2020-09-10Set Constrained Temporal Transformer for Set Supervised Action Segmentation | AISC
2020-09-10An overview of task-oriented dialog systems | AISC
2020-09-09Targeted Machine Learning for Data Science | AISC
2020-09-08Build next generation recommenders with NVIDIA Merlin | AISC
2020-09-02Principal Neighbourhood Aggregation for Graph Nets | AISC
2020-09-01DeepFakes & Explainable AI Applications in NLP, Biomedical & Malware Classification
2020-08-28AI Ethics Then & Now: A Look Back on the Last Five Years | AISC
2020-08-27Beyond Accuracy: Behavioral Testing of NLP Models with CheckList | AISC
2020-08-27The Summary Loop: Learning to Write Abstractive Summaries Without Examples + Demo | AISC
2020-08-26[MEM] Learning Permutation Invariant Representations using Memory Networks | AISC
2020-08-26AI for Fun!
2020-08-25[T-Fixup] Improving Transformer Optimization Through Better Initialization | AISC
2020-08-25A review of ML for aerospace systems health management | AISC
2020-08-21An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph | AISC
2020-08-20Overview of Synthetic Data and Simulations | AISC