Chris Russell
@cruss.bsky.social
Algorithmic governance and computer vision. Assoc Prof Oxford, Ellis fellow
Anyone interested can talk to Eoin Delany at poster 5502, or check out the paper for more details arxiv.org/abs/2407.13710. Great work by my co-authors, Eoin, Zihao Fu, @swachter.bsky.social and @bmittelstadt.bsky.social
OxonFair: A Flexible Toolkit for Algorithmic Fairness
We present OxonFair, a new open source toolkit for enforcing fairness in binary classification. Compared to existing toolkits: (i) We support NLP and Computer Vision classification as well as standard...
arxiv.org
December 11, 2024 at 11:29 AM
Anyone interested can talk to Eoin Delany at poster 5502, or check out the paper for more details arxiv.org/abs/2407.13710. Great work by my co-authors, Eoin, Zihao Fu, @swachter.bsky.social and @bmittelstadt.bsky.social
The trick is model surgery on a validation set. We train a multi-head model, the first head solves the original task and the other heads predict groups using a squared loss. A weighted sum of all these heads can enforce any fairness definition, and has the same architecture as the original net
December 11, 2024 at 11:29 AM
The trick is model surgery on a validation set. We train a multi-head model, the first head solves the original task and the other heads predict groups using a squared loss. A weighted sum of all these heads can enforce any fairness definition, and has the same architecture as the original net
Sorry, not this year. Maybe next time.
October 1, 2024 at 1:31 PM
Sorry, not this year. Maybe next time.
This is a common problem with LLMs if the temperature is set to zero. It might just be that these small models need a higher temperature.
January 1, 2024 at 12:13 PM
This is a common problem with LLMs if the temperature is set to zero. It might just be that these small models need a higher temperature.