Meta-Graph: Few-Shot Link Prediction Using Meta-Learning | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=3ELboSNn2JA


Duration: 53:31
664 views
16

Speaker(s): Avishek (Joey) Bose
Facilitator(s): Nabila Abraham

Find the recording, slides, and more info at https://ai.science/e/meta-graph-few-shot-link-prediction-using-meta-learning--mqol9BHPyj5ZFajdONQ5

Motivation / Abstract
Link prediction is a ubiqtuous task that can be applied to various real world scenarios including biomedical interaction networks, social networks and recommendation systems. The goal of link prediction is to learn from a graph to infer missing or previously unknown relationships. For instance, in a social network we may use link prediction to power a friendship recommendation system, or in the case of biological network data, link prediction might be used to infer possible relationships between drugs and diseases. However, previous work on link prediction generally focuses only on one particular problem setting: previous work generally assumes that link prediction is to be performed on a single dense graph, with at least 50% of the true edges observed during training. Bose and his co-authors investigate how to perform link prediction when only a sparse sample (less than 30%) of edges are available. The authors formulate link prediction as a few-shot learning problem and solve it via a multi-graph, meta-learning strategy. They experiment on 3 very different datasets and find that Meta-Graph has the strongest performance in the sparse data regime, acheiving new state of the art results on sparse graphs.

What was discussed?
- the difference between 'pre-training' and 'fine-tuning' in Meta-Graph
- the motivation for the meta-learning approach
- the rationale for VGAE as the baseline link prediction framework
- the importance of the graph signature function and what it represents
- future directions in scaling Meta-graph to heterogeneous graphs/knowledge graphs

What are the key takeaways?


------
#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


2020-06-25Memory-Based Graph Networks | AISC
2020-06-25Paper Explained : PEGASUS, a SOTA abstractive summarization model by Google | AISC
2020-06-24Towards Amortized Ranking-Critical Training for Collaborative Filtering | AISC
2020-06-24Paper review - Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey | AISC
2020-06-23Decoding our thoughts: Tracking the contents of (non)-conscious working memory | AISC
2020-06-23[XAI] Explainable AI in Retail | AISC
2020-06-22Why you should be part of AISC community!
2020-06-18Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning | AISC
2020-06-17GrowNet: Gradient Boosting Neural Networks | AISC
2020-06-17LogoGAN: Creating Logos with Generative Adversarial Networks | Workshop Capstone
2020-06-11Meta-Graph: Few-Shot Link Prediction Using Meta-Learning | AISC
2020-06-11Algorithmic Inclusion: A Scalable Approach to Reducing Gender Bias in Google Translate | AISC
2020-06-10Reinforcement Learning in Economics and Finance | AISC
2020-06-05Building (AI?) Products; Step by Step Guide | AISC
2020-06-03The Synthesizability of Molecules Proposed by Generative Models | AISC
2020-05-28A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosi
2020-05-28Unifying machine learning and quantum chemistry with a deep neural network | AISC
2020-05-27Model Selection for Optimal Prediction in Statistical Learning - Part 2 / 2 | AISC
2020-05-26Representation Learning of Histopathology Images using Graph Neural Networks | AISC
2020-05-26BillionX acceleration using AI Emulators | AISC
2020-05-22Machine Learning Methods for High Throughput Virtual Screening with a focus on Organic Photovoltaics