Search Results for author:
Found 15 papers, 3 papers with code
Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification
In this paper, we propose Prototype and Instance Contrastive Learning (PICL), a novel method for unsupervised domain adaptation in speaker verification through dual-level contrastive learning.
Unified Audio Event Detection
Sound Event Detection (SED) detects regions of sound events, while Speaker Diarization (SD) segments speech conversations attributed to individual speakers.
Riemannian Federated Learning via Averaging Gradient Stream
If decaying step sizes are used, the global convergence is established.
Federated Learning on Riemannian Manifolds with Differential Privacy
To the best of our knowledge, this is the first federated learning framework on Riemannian manifold with a privacy guarantee and convergence results.
Visual Hallucinations of Multi-modal Large Language Models
We find that existing MLLMs such as GPT-4V, LLaVA-1. 5, and MiniGPT-v2 hallucinate for a large fraction of the instances in our benchmark.
Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach
A major obstacle in this setting is the existence of compound biases from the observational data.
Data-Free Hard-Label Robustness Stealing Attack
In response to these identified gaps, we introduce a novel Data-Free Hard-Label Robustness Stealing (DFHL-RS) attack in this paper, which enables the stealing of both model accuracy and robustness by simply querying hard labels of the target model without the help of any natural data.
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.
A Robust Classifier Under Missing-Not-At-Random Sample Selection Bias
In this paper, we propose BiasCorr, an algorithm that improves on Greene's method by modifying the original training set in order for a classifier to learn under MNAR sample selection bias.
Achieving Counterfactual Fairness for Causal Bandit
In online recommendation, customers arrive in a sequential and stochastic manner from an underlying distribution and the online decision model recommends a chosen item for each arriving individual based on some strategy.
Recursive Importance Sketching for Rank Constrained Least Squares: Algorithms and High-order Convergence
In this paper, we propose {\it \underline{R}ecursive} {\it \underline{I}mportance} {\it \underline{S}ketching} algorithm for {\it \underline{R}ank} constrained least squares {\it \underline{O}ptimization} (RISRO).
Achieving User-Side Fairness in Contextual Bandits
Personalized recommendation based on multi-arm bandit (MAB) algorithms has shown to lead to high utility and efficiency as it can dynamically adapt the recommendation strategy based on feedback.
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.
Deep Denoising: Rate-Optimal Recovery of Structured Signals with a Deep Prior
Deep neural networks provide state-of-the-art performance for image denoising, where the goal is to recover a near noise-free image from a noisy image.
Rate-Optimal Denoising with Deep Neural Networks
Deep neural networks provide state-of-the-art performance for image denoising, where the goal is to recover a near noise-free image from a noisy observation.
