ExFaKT: a framework for explaining facts over knowledge graphs and text

ExFaKT: a framework for explaining facts over knowledge graphs and text Gad-Elrab et al., WSDM'19 Last week we took a look at Graph Neural Networks for learning with structured representations. Another kind of graph of interest for learning and inference is the knowledge graph. Knowledge Graphs (KGs) are large collections of factual triples of the … Continue reading ExFaKT: a framework for explaining facts over knowledge graphs and text

Graph neural networks: a review of methods and applications

Graph neural networks: a review of methods and applications Zhou et al., arXiv 2019 It’s another graph neural networks survey paper today! Cue the obligatory bus joke. Clearly, this covers much of the same territory as we looked at earlier in the week, but when we’re lucky enough to get two surveys published in short … Continue reading Graph neural networks: a review of methods and applications

A comprehensive survey on graph neural networks

A comprehensive survey on graph neural networks Wu et al., arXiv'19 Last year we looked at ‘Relational inductive biases, deep learning, and graph networks,’ where the authors made the case for deep learning with structured representations, which are naturally represented as graphs. Today’s paper choice provides us with a broad sweep of the graph neural … Continue reading A comprehensive survey on graph neural networks

TensorFlow.js: machine learning for the web and beyond

TensorFlow.js: machine learning for the web and beyond Smilkov et al., SysML'19 If machine learning and ML models are to pervade all of our applications and systems, then they’d better go to where the applications are rather than the other way round. Increasingly, that means JavaScript - both in the browser and on the server. … Continue reading TensorFlow.js: machine learning for the web and beyond

Fixed it for you: protocol repair using lineage graphs

Fixed it for you: protocol repair using lineage graphs Oldenburg et al., CIDR'19 This is a cool paper on a number of levels. Firstly, the main result that catches my eye is that it’s possible to build a distributed systems ‘debugger’ that can suggest protocol-level fixes. E.g. say you have a system that sometimes sends … Continue reading Fixed it for you: protocol repair using lineage graphs