activity
20172026
most citedDualPrompt: Complementary Prompting for Rehearsal-free Continual Learning

18 citations · 62 across the 19 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2023★ 1 cited

PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series

Nicasia Beebe-Wang, Sayna Ebrahimi, Jinsung Yoon +2

Real-world time series data that commonly reflect sequential human behavior are often uniquely irregularly sampled and sparse, with highly nonuniform sampling over time and entitie…

cs.LG2023★ 2 cited

LANISTR: Multimodal Learning from Structured and Unstructured Data

Sayna Ebrahimi, Sercan O. Arik, Yihe Dong +1

Multimodal large-scale pretraining has shown impressive performance for unstructured data such as language and image. However, a prevalent real-world scenario involves structured d…

cs.LG2023

ASPEST: Bridging the Gap Between Active Learning and Selective Prediction

Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi +3

Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. A…

cs.LG2022★ 18 cited

DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning

Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi +8

Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store pa…

cs.LG2021

Predicting with Confidence on Unseen Distributions

Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi +2

Recent work has shown that the performance of machine learning models can vary substantially when models are evaluated on data drawn from a distribution that is close to but differ…

cs.LG2020

Adversarial Continual Learning

Sayna Ebrahimi, Franziska Meier, Roberto Calandra +2

Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared st…