FairST combines 1D/2D/3D convolutions with fairness regularization using novel region-based and individual-based fairness gap metrics, reducing fairness gaps over 80% while improving accuracy over LSTMs, ConvLSTMs, and 3D CNNs on bike and ride share data.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2019 3verdicts
UNVERDICTED 3representative citing papers
QUOTIENT achieves 50X faster WAN training time and 6% higher absolute accuracy for secure two-party DNN training by jointly optimizing a discretized training algorithm with a tailored secure protocol.
Introduces hGAO and cGAO operators for graph representation learning that outperform standard graph attention operators in accuracy while reducing computational requirements.
citing papers explorer
-
FairST: Equitable Spatial and Temporal Demand Prediction for New Mobility Systems
FairST combines 1D/2D/3D convolutions with fairness regularization using novel region-based and individual-based fairness gap metrics, reducing fairness gaps over 80% while improving accuracy over LSTMs, ConvLSTMs, and 3D CNNs on bike and ride share data.
-
QUOTIENT: Two-Party Secure Neural Network Training and Prediction
QUOTIENT achieves 50X faster WAN training time and 6% higher absolute accuracy for secure two-party DNN training by jointly optimizing a discretized training algorithm with a tailored secure protocol.
-
Graph Representation Learning via Hard and Channel-Wise Attention Networks
Introduces hGAO and cGAO operators for graph representation learning that outperform standard graph attention operators in accuracy while reducing computational requirements.