8 citations · 11 across the 16 of their papers we have counts for
30 papers
Latent Information Sharing for Accelerating Federated Learning
Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos +2
Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, hindering the efficient train…
Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
Yigit Turkmen, Baturalp Buyukates, Melih Bastopcu
Large language models (LLMs) are often ensembled together to improve overall reliability and robustness, but in practice models are strongly correlated. This raises a fundamental q…
Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
Sungmin Kang, Yavuz Faruk Bakman, Duygu Nur Yaldiz +2
The rapid advancement of large language models (LLMs) has transformed the landscape of natural language processing, enabling breakthroughs across a wide range of areas including qu…
Balancing Information Accuracy and Response Timeliness in Networked LLMs
Yigit Turkmen, Baturalp Buyukates, Melih Bastopcu
Recent advancements in Large Language Models (LLMs) have transformed many fields including scientific discovery, content generation, biomedical text mining, and educational technol…
Reconsidering LLM Uncertainty Estimation Methods in the Wild
Yavuz Bakman, Duygu Nur Yaldiz, Sungmin Kang +4
Large Language Model (LLM) Uncertainty Estimation (UE) methods have become a crucial tool for detecting hallucinations in recent years. While numerous UE methods have been proposed…
Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models
Sizai Hou, Songze Li, Baturalp Buyukates
Prompt learning is a crucial technique for adapting pre-trained multimodal language models (MLLMs) to user tasks. Federated prompt personalization (FPP) is further developed to add…
FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling
Emir Ceyani, Han Xie, Baturalp Buyukates +2
Graphs are crucial for modeling relational and biological data. As datasets grow larger in real-world scenarios, the risk of exposing sensitive information increases, making privac…
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates +5
Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize…
Maverick-Aware Shapley Valuation for Client Selection in Federated Learning
Mengwei Yang, Ismat Jarin, Baturalp Buyukates +2
Federated Learning (FL) allows clients to train a model collaboratively without sharing their private data. One key challenge in practical FL systems is data heterogeneity, particu…
Renormalization Group flow, Optimal Transport and Diffusion-based Generative Model
Artan Sheshmani, Yi-Zhuang You, Baturalp Buyukates +2
Diffusion-based generative models represent a forefront direction in generative AI research today. Recent studies in physics have suggested that the renormalization group (RG) can…
MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates +3
Generative Large Language Models (LLMs) are widely utilized for their excellence in various tasks. However, their tendency to produce inaccurate or misleading outputs poses a poten…
Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification
Shanshan Han, Wenxuan Wu, Baturalp Buyukates +4
Federated Learning (FL) systems are susceptible to adversarial attacks, such as model poisoning attacks and backdoor attacks. Existing defense mechanisms face critical limitations…
FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
Shanshan Han, Baturalp Buyukates, Zijian Hu +13
This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defens…
Proof-of-Contribution-Based Design for Collaborative Machine Learning on Blockchain
Baturalp Buyukates, Chaoyang He, Shanshan Han +5
We consider a project (model) owner that would like to train a model by utilizing the local private data and compute power of interested data owners, i.e., trainers. Our goal is to…
Secure Federated Clustering
Songze Li, Sizai Hou, Baturalp Buyukates +1
We consider a foundational unsupervised learning task of -means data clustering, in a federated learning (FL) setting consisting of a central server and many distributed clients…
Version Age of Information in Clustered Gossip Networks
Baturalp Buyukates, Melih Bastopcu, Sennur Ulukus
We consider a network consisting of a single source and receiver nodes that are grouped into equal-sized clusters. We use cluster heads in each cluster to facilitate communicat…
Gossiping with Binary Freshness Metric
Melih Bastopcu, Baturalp Buyukates, Sennur Ulukus
We consider the binary freshness metric for gossip networks that consist of a single source and end-nodes, where the end-nodes are allowed to share their stored versions of the…
Age of Gossip in Networks with Community Structure
Baturalp Buyukates, Melih Bastopcu, Sennur Ulukus
We consider a network consisting of a single source and receiver nodes that are grouped into equal size communities, i.e., clusters, where each cluster includes nodes a…
Gradient Coding with Dynamic Clustering for Straggler-Tolerant Distributed Learning
Baturalp Buyukates, Emre Ozfatura, Sennur Ulukus +1
Distributed implementations are crucial in speeding up large scale machine learning applications. Distributed gradient descent (GD) is widely employed to parallelize the learning t…
Timely Communication in Federated Learning
Baturalp Buyukates, Sennur Ulukus
We consider a federated learning framework in which a parameter server (PS) trains a global model by using clients without actually storing the client data centrally at a cloud…
Gradient Coding with Dynamic Clustering for Straggler Mitigation
Baturalp Buyukates, Emre Ozfatura, Sennur Ulukus +1
In distributed synchronous gradient descent (GD) the main performance bottleneck for the per-iteration completion time is the slowest \textit{straggling} workers. To speed up GD it…
Age-Based Coded Computation for Bias Reduction in Distributed Learning
Emre Ozfatura, Baturalp Buyukates, Deniz Gunduz +1
Coded computation can be used to speed up distributed learning in the presence of straggling workers. Partial recovery of the gradient vector can further reduce the computation tim…
Selective Encoding Policies for Maximizing Information Freshness
Melih Bastopcu, Baturalp Buyukates, Sennur Ulukus
An information source generates independent and identically distributed status update messages from an observed random phenomenon which takes distinct values based on a given p…
Age of Information with Gilbert-Elliot Servers and Samplers
Baturalp Buyukates, Sennur Ulukus
We study age of information in a status updating system that consists of a single sampler, i.e., source node, that sends time-sensitive status updates to a single monitor node thro…