14 citations · 21 across the 8 of their papers we have counts for
8 papers
Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks
Yuntian He, Pranav Maneriker, Anutam Srinivasan +2
Conformal Prediction is a robust framework that ensures reliable coverage across machine learning tasks. Although recent studies have applied conformal prediction to graph neural n…
Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs
Pranav Maneriker, Aditya T. Vadlamani, Anutam Srinivasan +3
Conformal prediction has become increasingly popular for quantifying the uncertainty associated with machine learning models. Recent work in graph uncertainty quantification has bu…
HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs
Yue Zhang, Yuntian He, Saket Gurukar +1
Heterogeneous graphs are ubiquitous in real-world applications because they can represent various relationships between different types of entities. Therefore, learning embeddings…
FairMILE: Towards an Efficient Framework for Fair Graph Representation Learning
Yuntian He, Saket Gurukar, Srinivasan Parthasarathy
Graph representation learning models have demonstrated great capability in many real-world applications. Nevertheless, prior research indicates that these models can learn biased r…
Sepsis Prediction with Temporal Convolutional Networks
Xing Wang, Yuntian He
We design and implement a temporal convolutional network model to predict sepsis onset. Our model is trained on data extracted from MIMIC III database, based on a retrospective ana…
FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification
Sean Current, Yuntian He, Saket Gurukar +1
As machine learning becomes more widely adopted across domains, it is critical that researchers and ML engineers think about the inherent biases in the data that may be perpetuated…
SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis
Pranav Maneriker, Yuntian He, Srinivasan Parthasarathy
Darknet market forums are frequently used to exchange illegal goods and services between parties who use encryption to conceal their identities. The Tor network is used to host the…
Cost-Effective Seed Selection in Online Social Networks
Kai Han, Yuntian He, Xiaokui Xiao +3
We study the min-cost seed selection problem in online social networks, where the goal is to select a set of seed nodes with the minimum total cost such that the expected number of…