Anonymous Walk Embeddings | ML with Graphs (Research Paper Walkthrough)

#graphembedding #machinelearning #research
The research talks about using Random Walk inspired Anonymous Walks as graph units to derive feature-based and data-driven graph embeddings. Watch to know more :)

⏩ Abstract: The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.

Please feel free to share out the content and subscribe to my channel :)

⏩ OUTLINE:
0:00 - Abstract
01:06 - Anonymous Walks
05:56 - Rationale for Anonymous Walks
07:00 - AWE: Feature-based Model
11:54 - Sampling in AWE Feature-based Model
14:30 - AWE: data-driven Model

⏩ Paper Title: Anonymous Walk Embeddings
⏩ Author: Sergey Ivanov, Evgeny Burnaev
⏩ Organisation: Skolkovo Institute of Science and Technology, Moscow, Russia | Criteo Research, Paris, France

⏩ IMPORTANT LINKS
Reconstructing Markov Processes from

*********************************************
If you want to support me financially which totally optional and voluntary :) ❤️

*********************************************
*********************************************

Tools I use for making videos :)

#techviz #datascienceguy #ml_with_graphs #representation #learning

[cobaltfolly]

Thank you, this was a helpful video. When calculating the graph embedding f_G, the authors assume that the length of anonymous walk L is fixed. I was wondering how L is chosen. If one does not fix L, I believe there will be multiple graph embeddings {f_G} for the same graph, i.e. one for each L.