5 papers
Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning
Connor Mclaughlin, Nigel Lee, Lili Su
Machine learning models often need to adapt to new data after deployment due to structured or unstructured real-world dynamics. The Continual Learning (CL) framework enables contin…
On the Power of Source Screening for Learning Shared Feature Extractors
Leo Muxing Wang, Connor Mclaughlin, Lili Su
Learning with shared representation is widely recognized as an effective way to separate commonalities from heterogeneity across various heterogeneous sources. Most existing work i…
Mahalanobis-Aware Training for Out-of-Distribution Detection
Connor Mclaughlin, Jason Matterer, Michael Yee
While deep learning models have seen widespread success in controlled environments, there are still barriers to their adoption in open-world settings. One critical task for safe de…
Network Fault-tolerant and Byzantine-resilient Social Learning via Collaborative Hierarchical Non-Bayesian Learning
Connor Mclaughlin, Matthew Ding, Denis Edogmus +1
As the network scale increases, existing fully distributed solutions start to lag behind the real-world challenges such as (1) slow information propagation, (2) network communicati…
Fast and Robust State Estimation and Tracking via Hierarchical Learning
Connor Mclaughlin, Matthew Ding, Deniz Erdogmus +1
Fast and reliable state estimation and tracking are essential for real-time situation awareness in Cyber-Physical Systems (CPS) operating in tactical environments or complicated ci…