Search Results for author:
Found 17 papers, 6 papers with code
Long-Term Fair Decision Making through Deep Generative Models
This paper studies long-term fair machine learning which aims to mitigate group disparity over the long term in sequential decision-making systems.
Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective
To address this, we define a fair pruning task where a sparse model is derived subject to fairness requirements.
SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models
Specifically, SiDA attains a remarkable speedup in MoE inference with up to 3. 93X throughput increasing, up to 75% latency reduction, and up to 80% GPU memory saving with down to 1% performance drop.
From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling
Deep generative models have shown tremendous success in data density estimation and data generation from finite samples.
Algorithmic Recourse for Anomaly Detection in Multivariate Time Series
Anomaly detection in multivariate time series has received extensive study due to the wide spectrum of applications.
Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach
We focus on a decentralized notion of Differential Privacy, namely Local Differential Privacy, and apply randomization mechanisms to perturb both feature and label data at the node level before the data is collected by a central server for model training.
Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms
We propose ICM-VAE, a framework for learning causally disentangled representations supervised by causally related observed labels.
Achieving Counterfactual Fairness for Anomaly Detection
Ensuring fairness in anomaly detection models has received much attention recently as many anomaly detection applications involve human beings.
On Root Cause Localization and Anomaly Mitigation through Causal Inference
After that, we further propose an anomaly mitigation approach that aims to recommend mitigation actions on abnormal features to revert the abnormal outcomes such that the counterfactuals guided by the causal mechanism are normal.
Fair Multiple Decision Making Through Soft Interventions
Previous research in fair classification mostly focuses on a single decision model.
Fairness through Equality of Effort
We develop algorithms for determining whether an individual or a group of individuals is discriminated in terms of equality of effort.
PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
A recent trend of fair machine learning is to define fairness as causality-based notions which concern the causal connection between protected attributes and decisions.
Fairness-aware Classification: Criterion, Convexity, and Bounds
In this paper, we propose a general framework for learning fair classifiers which addresses previous limitations.
On Discrimination Discovery and Removal in Ranked Data using Causal Graph
Existing methods in fairness-aware ranking are mainly based on statistical parity that cannot measure the true discriminatory effect since discrimination is causal.
Achieving non-discrimination in prediction
Based on the results, we develop a two-phase framework for constructing a discrimination-free classifier with a theoretical guarantee.
Achieving non-discrimination in data release
Discrimination discovery and prevention/removal are increasingly important tasks in data mining.
A causal framework for discovering and removing direct and indirect discrimination
In this paper, we investigate the problem of discovering both direct and indirect discrimination from the historical data, and removing the discriminatory effects before the data is used for predictive analysis (e. g., building classifiers).
