activity
20172022
most citedOpportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams

11 citations · 28 across the 7 of their papers we have counts for

collaborators

12 papers

cs.LG2022

Heterogenous Ensemble of Models for Molecular Property Prediction

Sajad Darabi, Shayan Fazeli, Jiwei Liu +4

Previous works have demonstrated the importance of considering different modalities on molecules, each of which provide a varied granularity of information for downstream property…

cs.LG20211 cited

Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain

Sajad Darabi, Shayan Fazeli, Ali Pazoki +2

Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These metho…

cs.LG20211 cited

Synthesising Multi-Modal Minority Samples for Tabular Data

Sajad Darabi, Yotam Elor

Real-world binary classification tasks are in many cases imbalanced, where the minority class is much smaller than the majority class. This skewness is challenging for machine lear…

cs.LG2019

Group-Connected Multilayer Perceptron Networks

Mohammad Kachuee, Sajad Darabi, Shayan Fazeli +1

Despite the success of deep learning in domains such as image, voice, and graphs, there has been little progress in deep representation learning for domains without a known structu…

cs.LG20194 cited

Unsupervised Representation for EHR Signals and Codes as Patient Status Vector

Sajad Darabi, Mohammad Kachuee, Majid Sarrafzadeh

Effective modeling of electronic health records presents many challenges as they contain large amounts of irregularity most of which are due to the varying procedures and diagnosis…

cs.LG2019

TAPER: Time-Aware Patient EHR Representation

Sajad Darabi, Mohammad Kachuee, Shayan Fazeli +1

Effective representation learning of electronic health records is a challenging task and is becoming more important as the availability of such data is becoming pervasive. The data…