Search Results for author:
Found 25 papers, 10 papers with code
Automatic Calibration for Membership Inference Attack on Large Language Models
Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs).
MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training
In the diverse field of medical imaging, automatic segmentation has numerous applications and must handle a wide variety of input domains, such as different types of Computed Tomography (CT) scans and Magnetic Resonance (MR) images.
Byzantine-Robust Decentralized Federated Learning
However, due to its fully decentralized nature, DFL is highly vulnerable to poisoning attacks, where malicious clients could manipulate the system by sending carefully-crafted local models to their neighboring clients.
Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
A popular approach to mitigate impacts of incomplete client participation is the server-assisted federated learning (SA-FL) framework, where the server is equipped with an auxiliary dataset.
Learning to Poison Large Language Models for Downstream Manipulation
The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities.
FedDRO: Federated Compositional Optimization for Distributionally Robust Learning
A key novelty of our work is to develop solution accuracy-independent algorithms that do not require large batch gradients (and function evaluations) for solving federated CO problems.
GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation
In geographical image segmentation, performance is often constrained by the limited availability of training data and a lack of generalizability, particularly for segmenting mobility infrastructure such as roads, sidewalks, and crosswalks.
Hijacking Large Language Models via Adversarial In-Context Learning
In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts.
Interpretability-Aware Vision Transformer
Furthermore, if ViTs are not properly trained with the given data and do not prioritize the region of interest, the {\it post hoc} methods would be less effective.
AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation
By eliminating the need for manual prompts, it enhances SAM's capabilities for 3D medical image segmentation and achieves state-of-the-art (SOTA) performance in CT-based multi-organ segmentation tasks.
An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning
Overall, we hope that this article can serve to accelerate the adoption of BLO as a generic tool to model, analyze, and innovate on a wide array of emerging SP and ML applications.
Fairness-aware Vision Transformer via Debiased Self-Attention
Notably, DSA leverages adversarial examples to locate and mask the spurious features in the input image patches with an additional attention weights alignment regularizer in the training objective to encourage learning real features for target prediction.
DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization
Decentralized bilevel optimization has received increasing attention recently due to its foundational role in many emerging multi-agent learning paradigms (e. g., multi-agent meta-learning and multi-agent reinforcement learning) over peer-to-peer edge networks.
FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images
Computed Tomography (CT) based precise prostate segmentation for treatment planning is challenging due to (1) the unclear boundary of the prostate derived from CT's poor soft tissue contrast and (2) the limitation of convolutional neural network-based models in capturing long-range global context.
INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks
Our main contributions in this paper are two-fold: i) We first propose a deterministic algorithm called INTERACT (inner-gradient-descent-outer-tracked-gradient) that requires the sample complexity of $\mathcal{O}(n \epsilon^{-1})$ and communication complexity of $\mathcal{O}(\epsilon^{-1})$ to solve the bilevel optimization problem, where $n$ and $\epsilon > 0$ are the number of samples at each agent and the desired stationarity gap, respectively.
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
We first show that the commonly-used Fast-AT is equivalent to using a stochastic gradient algorithm to solve a linearized BLO problem involving a sign operation.
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach
We analyze the optimization and the generalization performance of the proposed framework for the $\ell_2$ loss.
Anarchic Federated Learning
To satisfy the need for flexible worker participation, we consider a new FL paradigm called "Anarchic Federated Learning" (AFL) in this paper.
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
Despite extensive research, for a generic non-convex FL problem, it is not clear, how to choose the WNs' and the server's update directions, the minibatch sizes, and the local update frequency, so that the WNs use the minimum number of samples and communication rounds to achieve the desired solution.
A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum
We focus on bilevel problems where the lower level subproblem is strongly-convex and the upper level objective function is smooth.
Joint Collaboration and Compression Design for Distributed Sequential Estimation in a Wireless Sensor Network
We propose two versions of compression design, one centralized where the compression strategies are derived at the FC and the other decentralized, where the local sensors compute their individual compression matrices independently.
Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction
In this work, we propose a distributed algorithm for stochastic non-convex optimization.
Optimization and Control Distributed, Parallel, and Cluster Computing
Parallel Restarted SPIDER -- Communication Efficient Distributed Nonconvex Optimization with Optimal Computation Complexity
For online problems ($n$ unknown or infinite), we achieve the optimal IFO complexity $O(\epsilon^{-3/2})$.
Why Interpretability in Machine Learning? An Answer Using Distributed Detection and Data Fusion Theory
Such arguments, however, fail to acknowledge that the overall decision-making system is composed of two entities: the learned model and a human who fuses together model outputs with his or her own information.
Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach
This paper considers the problem of high dimensional signal detection in a large distributed network whose nodes can collaborate with their one-hop neighboring nodes (spatial collaboration).
