By Kyra Yee and Irene Font Peradejordi on
Sharing learnings from the first algorithmic bias bounty challenge
By Kristopher Kirkland on
How Twitter moved from a home grown logging platform to the commercially available Splunk and the challenges we’ve encountered along the way.
By Dom Del Nano on
Describe how the Observability team applied Flame graphs to a novel use case (internal usage of Twitter’s time series database) outside of their typical application
By Rumman Chowdhury and Jutta Williams on
As part of this year’s DEFCON AI Village, we’re trying something radical by introducing the industry’s first algorithmic bias bounty competition.
By Ben Chamberlain and Michael Bronstein on
In this post, we will discuss our recent work on neural graph diffusion networks.
By Fabrizio Frasca and Michael Bronstein on
Twitter describes how to design local and computationally efficient provably powerful graph neural networks.
By Rumman Chowdhury on
Twitter shares a technical analysis of its assessment for potential bias in its image cropping algorithm as part of its efforts to be more transparent around how it uses machine learning to improve pe
By Yang Shi on
Twitter engineers found and fixed a Linux kernel bug in memory shrinker which caused OOM for us.
By Michael Bronstein on
This blog post is based on Michael Bronstein’s keynote talk at ICLR 2021 and the paper M. M. Bronstein et al., Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges (2021)
By Rakshit Wadhwa and Ryan Turner on
Twitter annotated its data to a defined taxonomy by leveraging machine learning in its data platform by fusing Elasticsearch with neural networks.