activity
20202023
most citedREST: Relational Event-driven Stock Trend Forecasting

47 citations · 78 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2023★ 1 cited

Selective Pre-training for Private Fine-tuning

Da Yu, Sivakanth Gopi, Janardhan Kulkarni +5

Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are…

cs.LG2022★ 5 cited

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent

Da Yu, Gautam Kamath, Janardhan Kulkarni +3

Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all d…

cs.LG2022

Anomaly Detection by Leveraging Incomplete Anomalous Knowledge with Anomaly-Aware Bidirectional GANs

Bowen Tian, Qinliang Su, Jian Yin

The goal of anomaly detection is to identify anomalous samples from normal ones. In this paper, a small number of anomalies are assumed to be available at the training stage, but t…

cs.LG2021

Availability Attacks Create Shortcuts

Da Yu, Huishuai Zhang, Wei Chen +2

Availability attacks, which poison the training data with imperceptible perturbations, can make the data \emph{not exploitable} by machine learning algorithms so as to prevent unau…

cs.LG2021

Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer

Siyuan Liu, Yusong Wang, Tong Wang +6

The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential ro…

cs.LG2021★ 5 cited

Instance-wise Graph-based Framework for Multivariate Time Series Forecasting

Wentao Xu, Weiqing Liu, Jiang Bian +2

The multivariate time series forecasting has attracted more and more attention because of its vital role in different fields in the real world, such as finance, traffic, and weathe…