Digests » 89

this week's favorite

A Gentle Introduction to Deep Learning for Graphs

The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is designed as a tutorial introduction to the field of deep learning for graphs.

Google just published 25 million free datasets

Here’s what you need to know about the largest data repository in the world.

Counterfactual Explanations offer clarity in AI decision-making

Consider a person who applies for a loan with a financial company, but their application is rejected by a machine learning algorithm used to determine who receives a loan from the company. How would you explain the decision made by the algorithm to this person? One option is to provide them with a list of features that contributed to the algorithm’s decision, such as income and credit score. Many of the current explanation methods provide this information by either analyzing the algorithm’s properties or approximating it with a simpler, interpretable model.

SpaceOpt: optimize discrete search space via gradient boosting regression

SpaceOpt is an optimization algorithm for discrete search spaces that uses gradient boosting regression to find the most promising candidates for evaluation by predicting their evaluation score. Training data is gathered sequentially and random or human-guided exploration can be easily incorporated at any stage.

Thinc · A refreshing functional take on deep learning

A refreshing functional take on deep learning, compatible with your favorite libraries.


Karate Club: an unsupervised machine learning extension for NetworkX

Karate Club consists of state-of-the-art methods to do unsupervised learning on graph structured data. To put it simply it is a Swiss Army knife for small-scale graph mining research. First, it provides network embedding techniques at the node and graph level. Second, it includes a variety of overlapping and non-overlapping community detection methods. Implemented methods cover a wide range of network science (NetSci, Complenet), data mining (ICDM, CIKM, KDD), artificial intelligence (AAAI, IJCAI) and machine learning (NeurIPS, ICML, ICLR) conferences, workshops, and pieces from prominent journals.