1 code implementation • 26 Mar 2024 • Leonidas Gee, Andrea Zugarini, Novi Quadrianto
To reduce the inference cost of large language models, model compression is increasingly used to create smaller scalable models.
1 code implementation • 29 Nov 2023 • Gergely Dániel Németh, Miguel Ángel Lozano, Novi Quadrianto, Nuria Oliver
In this paper, we show that the effectiveness of these attacks on the clients negatively correlates with the size of the client datasets and model complexity.
no code implementations • 2 Feb 2023 • Ainhize Barrainkua, Paula Gordaliza, Jose A. Lozano, Novi Quadrianto
Several recent works encourage the use of a Bayesian framework when assessing performance and fairness metrics of a classification algorithm in a supervised setting.
no code implementations • 14 Nov 2022 • Ainhize Barrainkua, Paula Gordaliza, Jose A. Lozano, Novi Quadrianto
Human lives are increasingly being affected by the outcomes of automated decision-making systems and it is essential for the latter to be, not only accurate, but also fair.
1 code implementation • 7 Nov 2022 • Myles Bartlett, Sara Romiti, Viktoriia Sharmanska, Novi Quadrianto
In order to perform the online matching in a runtime- and memory-efficient way, we draw upon the self-supervised literature and combine a memory bank with a slow-moving momentum encoder.
no code implementations • 27 Sep 2022 • Gergely Dániel Németh, Miguel Ángel Lozano, Novi Quadrianto, Nuria Oliver
Federated learning (FL) has been proposed as a privacy-preserving approach in distributed machine learning.
1 code implementation • 3 Aug 2022 • Sara Romiti, Christopher Inskip, Viktoriia Sharmanska, Novi Quadrianto
We demonstrate the effectiveness of RealPatch on three benchmark datasets, CelebA, Waterbirds and a subset of iWildCam, showing improvements in worst-case subgroup performance and in subgroup performance gap in binary classification.
1 code implementation • 24 Mar 2022 • Thomas Kehrenberg, Myles Bartlett, Viktoriia Sharmanska, Novi Quadrianto
We investigate a scenario in which the absence of certain data is linked to the second level of a two-level hierarchy in the data.
no code implementations • 1 Jan 2021 • Thomas Kehrenberg, Viktoriia Sharmanska, Myles Scott Bartlett, Novi Quadrianto
In a statistical notion of algorithmic fairness, we partition individuals into groups based on some key demographic factors such as race and gender, and require that some statistics of a classifier be approximately equalized across those groups.
1 code implementation • ECCV 2020 • Thomas Kehrenberg, Myles Bartlett, Oliver Thomas, Novi Quadrianto
We propose to learn invariant representations, in the data domain, to achieve interpretability in algorithmic fairness.
Ranked #1 on Image Classification on CelebA 64x64
no code implementations • 14 Apr 2020 • Viktoriia Sharmanska, Lisa Anne Hendricks, Trevor Darrell, Novi Quadrianto
Computer vision algorithms, e. g. for face recognition, favour groups of individuals that are better represented in the training data.
no code implementations • 12 Mar 2020 • Bradley Butcher, Vincent S. Huang, Jeremy Reffin, Sema K. Sgaier, Grace Charles, Novi Quadrianto
Here we propose a causal extension to the datasheet concept proposed by Gebru et al (2018) to include approximate BN performance expectations for any given dataset.
1 code implementation • 22 Nov 2019 • Artyom Gadetsky, Kirill Struminsky, Christopher Robinson, Novi Quadrianto, Dmitry Vetrov
Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates.
no code implementations • pproximateinference AABI Symposium 2019 • Iuliia Molchanova, Dmitry Molchanov, Novi Quadrianto, Dmitry Vetrov
In this work we construct flexible joint distributions from low-dimensional conditional semi-implicit distributions.
1 code implementation • CVPR 2019 • Novi Quadrianto, Viktoriia Sharmanska, Oliver Thomas
On face images of the recent DiF dataset, with the same gender attribute, our method adjusts nose regions.
1 code implementation • 12 Oct 2018 • Thomas Kehrenberg, Zexun Chen, Novi Quadrianto
The issue of fairness in machine learning models has recently attracted a lot of attention as ensuring it will ensure continued confidence of the general public in the deployment of machine learning systems.
no code implementations • NeurIPS 2017 • Novi Quadrianto, Viktoriia Sharmanska
We set an overarching goal to develop a unified machine learning framework that is able to handle any definitions of fairness, their combinations, and also new definitions that might be stipulated in the future.
no code implementations • ICML 2017 • Xiuyan Ni, Novi Quadrianto, Yusu Wang, Chao Chen
Clustering data with both continuous and discrete attributes is a challenging task.
no code implementations • 14 Sep 2016 • Pietro Galliani, Amir Dezfouli, Edwin V. Bonilla, Novi Quadrianto
We develop an automated variational inference method for Bayesian structured prediction problems with Gaussian process (GP) priors and linear-chain likelihoods.
no code implementations • CVPR 2016 • Viktoriia Sharmanska, Novi Quadrianto
Can we learn about object classes in images by looking at a collection of relevant 3D models?
no code implementations • CVPR 2016 • Viktoriia Sharmanska, Daniel Hernandez-Lobato, Jose Miguel Hernandez-Lobato, Novi Quadrianto
On the technical side, we propose a framework to incorporate annotation disagreements into the classifiers.
no code implementations • 1 Oct 2014 • Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert
We interpret these methods as learning easiness and hardness of the objects in the privileged space and then transferring this knowledge to train a better classifier in the original space.
no code implementations • NeurIPS 2014 • Daniel Hernández-Lobato, Viktoriia Sharmanska, Kristian Kersting, Christoph H. Lampert, Novi Quadrianto
That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function.
no code implementations • 26 Sep 2013 • Novi Quadrianto, Viktoriia Sharmanska, David A. Knowles, Zoubin Ghahramani
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data.
1 code implementation • 15 Jul 2013 • Sebastien Bratieres, Novi Quadrianto, Zoubin Ghahramani
We introduce a conceptually novel structured prediction model, GPstruct, which is kernelized, non-parametric and Bayesian, by design.
no code implementations • NeurIPS 2010 • Novi Quadrianto, James Petterson, Tibério S. Caetano, Alex J. Smola, S. V. N. Vishwanathan
We propose an algorithm to perform multitask learning where each task has potentially distinct label sets and label correspondences are not readily available.
no code implementations • NeurIPS 2010 • Gilbert Leung, Novi Quadrianto, Kostas Tsioutsiouliklis, Alex J. Smola
We present a fast online solver for large scale maximum-flow problems as they occur in portfolio optimization, inventory management, computer vision, and logistics.
no code implementations • NeurIPS 2009 • Novi Quadrianto, James Petterson, Alex J. Smola
Many transductive inference algorithms assume that distributions over training and test estimates should be related, e. g. by providing a large margin of separation on both sets.
no code implementations • NeurIPS 2009 • Novi Quadrianto, John Lim, Dale Schuurmans, Tibério S. Caetano
The second is a min-min reformulation consisting of fast alternating steps of closed-form updates.
no code implementations • NeurIPS 2008 • Novi Quadrianto, Le Song, Alex J. Smola
Object matching is a fundamental operation in data analysis.