activity
20122024
most citedGuess Who Rated This Movie: Identifying Users Through Subspace Clustering

15 citations · 48 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2024

Learning Set Functions with Implicit Differentiation

Gözde Özcan, Chengzhi Shi, Stratis Ioannidis

Ou et al. (2022) introduce the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility functi…

cs.LG2024

T-PRIME: Transformer-based Protocol Identification for Machine-learning at the Edge

Mauro Belgiovine, Joshua Groen, Miquel Sirera +5

Spectrum sharing allows different protocols of the same standard (e.g., 802.11 family) or different standards (e.g., LTE and DVB) to coexist in overlapping frequency bands. As this…

cs.LG2023

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Max Torop, Aria Masoomi, Davin Hill +3

Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-…

cs.LG20232 cited

Towards Bias Correction of FedAvg over Nonuniform and Time-Varying Communications

Ming Xiang, Stratis Ioannidis, Edmund Yeh +2

Federated learning (FL) is a decentralized learning framework wherein a parameter server (PS) and a collection of clients collaboratively train a model via minimizing a global obje…

cs.LG20234 cited

DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning

Zifeng Wang, Zheng Zhan, Yifan Gong +4

Rehearsal-based approaches are a mainstay of continual learning (CL). They mitigate the catastrophic forgetting problem by maintaining a small fixed-size buffer with a subset of da…

cs.LG20239 cited

Explanations of Black-Box Models based on Directional Feature Interactions

Aria Masoomi, Davin Hill, Zhonghui Xu +5

As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain bl…