Search Results for author:
Found 30 papers, 10 papers with code
Are Compressed Language Models Less Subgroup Robust?
To reduce the inference cost of large language models, model compression is increasingly used to create smaller scalable models.
Addressing Membership Inference Attack in Federated Learning with Model Compression
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.
Uncertainty in Fairness Assessment: Maintaining Stable Conclusions Despite Fluctuations
Several recent works encourage the use of a Bayesian framework when assessing performance and fairness metrics of a classification algorithm in a supervised setting.
A Survey on Preserving Fairness Guarantees in Changing Environments
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.
Okapi: Generalising Better by Making Statistical Matches Match
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.
A Snapshot of the Frontiers of Client Selection in Federated Learning
Federated learning (FL) has been proposed as a privacy-preserving approach in distributed machine learning.
RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
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.
Addressing Missing Sources with Adversarial Support-Matching
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.
Zero-shot Fairness with Invisible Demographics
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.
Null-sampling for Interpretable and Fair Representations
We propose to learn invariant representations, in the data domain, to achieve interpretability in algorithmic fairness.
Ranked #1 on
Image Classification
on CelebA 64x64
Contrastive Examples for Addressing the Tyranny of the Majority
Computer vision algorithms, e. g. for face recognition, favour groups of individuals that are better represented in the training data.
Causal datasheet: An approximate guide to practically assess Bayesian networks in the real world
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.
Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution
Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates.
Structured Semi-Implicit Variational Inference
In this work we construct flexible joint distributions from low-dimensional conditional semi-implicit distributions.
Tuning Fairness by Balancing Target Labels
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.
Recycling Privileged Learning and Distribution Matching for Fairness
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.
Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data
Clustering data with both continuous and discrete attributes is a challenging task.
Gray-box inference for structured Gaussian process models
We develop an automated variational inference method for Bayesian structured prediction problems with Gaussian process (GP) priors and linear-chain likelihoods.
Learning From the Mistakes of Others: Matching Errors in Cross-Dataset Learning
Can we learn about object classes in images by looking at a collection of relevant 3D models?
Ambiguity Helps: Classification With Disagreements in Crowdsourced Annotations
On the technical side, we propose a framework to incorporate annotation disagreements into the classifiers.
Learning to Transfer Privileged Information
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.
Mind the Nuisance: Gaussian Process Classification using Privileged Noise
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.
The Supervised IBP: Neighbourhood Preserving Infinite Latent Feature Models
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data.
Bayesian Structured Prediction Using Gaussian Processes
We introduce a conceptually novel structured prediction model, GPstruct, which is kernelized, non-parametric and Bayesian, by design.
Optimal Web-Scale Tiering as a Flow Problem
We present a fast online solver for large scale maximum-flow problems as they occur in portfolio optimization, inventory management, computer vision, and logistics.
Multitask Learning without Label Correspondences
We propose an algorithm to perform multitask learning where each task has potentially distinct label sets and label correspondences are not readily available.
Distribution Matching for Transduction
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.
Convex Relaxation of Mixture Regression with Efficient Algorithms
The second is a min-min reformulation consisting of fast alternating steps of closed-form updates.
