Greg Ver Steeg

Fast Graph Learning with Unique Optimal Solutions

Feb 21, 2021
Sami Abu-El-Haija, Valentino Crespi, Greg Ver Steeg, Aram Galstyan

Access Paper or Ask Questions

Improved Brain Age Estimation with Slice-based Set Networks

Feb 09, 2021
Umang Gupta, Pradeep K. Lam, Greg Ver Steeg, Paul M. Thompson

* To appear at IEEE International Symposium on Biomedical Imaging 2021 (ISBI 2021). Code is available at https://git.io/JtazG

Access Paper or Ask Questions

Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning

Feb 08, 2021
Elan Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Sami Abu-El-Haija, Bryan Perozzi, Greg Ver Steeg, Aram Galstyan

* To appear in ICLR 2021

Access Paper or Ask Questions

Likelihood Ratio Exponential Families

Jan 15, 2021
Rob Brekelmans, Frank Nielsen, Alireza Makhzani, Aram Galstyan, Greg Ver Steeg

* NeurIPS Workshop on Deep Learning through Information Geometry

Access Paper or Ask Questions

Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation

Jan 11, 2021
Umang Gupta, Aaron Ferber, Bistra Dilkina, Greg Ver Steeg

* To appear in Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-21)

Access Paper or Ask Questions

Annealed Importance Sampling with q-Paths

Dec 14, 2020
Rob Brekelmans, Vaden Masrani, Thang Bui, Frank Wood, Aram Galstyan, Greg Ver Steeg, Frank Nielsen

* NeurIPS Workshop on Deep Learning through Information Geometry (Best Paper Award)

Access Paper or Ask Questions

Compressing Deep Neural Networks via Layer Fusion

Jul 29, 2020
James O' Neill, Greg Ver Steeg, Aram Galstyan

Access Paper or Ask Questions

Robust Classification under Class-Dependent Domain Shift

Jul 10, 2020
Tigran Galstyan, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan

* Accepted at ICML 2020 workshop on Uncertainty and Robustness in Deep Learning

Access Paper or Ask Questions

All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference

Jul 01, 2020
Rob Brekelmans, Vaden Masrani, Frank Wood, Greg Ver Steeg, Aram Galstyan

* ICML 2020

Access Paper or Ask Questions

Latent Embeddings of Point Process Excitations

Jun 02, 2020
Myrl G. Marmarelis, Greg Ver Steeg, Aram Galstyan

* 8 pages

Access Paper or Ask Questions

Overview of Scanner Invariant Representations

May 29, 2020
Daniel Moyer, Greg Ver Steeg, Paul M. Thompson

* Accepted as a short paper in MIDL 2020. In accordance with the MIDL 2020 Call for Papers, this short paper is an overview of an already published work arXiv:1904.05375, and was submitted to MIDL in order to allow presentation and discussion at the meeting

Access Paper or Ask Questions

Event Cartography: Latent Point Process Embeddings

May 05, 2020
Myrl G. Marmarelis, Greg Ver Steeg, Aram Galstyan

* 8 pages

Access Paper or Ask Questions

Improving Generalization by Controlling Label-Noise Information in Neural Network Weights

Feb 19, 2020
Hrayr Harutyunyan, Kyle Reing, Greg Ver Steeg, Aram Galstyan

Access Paper or Ask Questions

Discovery and Separation of Features for Invariant Representation Learning

Dec 02, 2019
Ayush Jaiswal, Rob Brekelmans, Daniel Moyer, Greg Ver Steeg, Wael AbdAlmageed, Premkumar Natarajan

* 10 pages, 3 figures

Access Paper or Ask Questions

Invariant Representations through Adversarial Forgetting

Nov 20, 2019
Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg, Wael AbdAlmageed, Premkumar Natarajan

* To appear in Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-20)

Access Paper or Ask Questions

Nearly-Unsupervised Hashcode Representations for Relation Extraction

Sep 09, 2019
Sahil Garg, Aram Galstyan, Greg Ver Steeg, Guillermo Cecchi

* Proceedings of EMNLP-19

Access Paper or Ask Questions

Efficient Covariance Estimation from Temporal Data

May 30, 2019
Hrayr Harutyunyan, Daniel Moyer, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan

Access Paper or Ask Questions

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

May 28, 2019
Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan

Access Paper or Ask Questions

MixHop: Higher-Order Graph Convolution Architectures via Sparsified Neighborhood Mixing

Apr 30, 2019
Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Hrayr Harutyunyan, Nazanin Alipourfard, Kristina Lerman, Greg Ver Steeg, Aram Galstyan

* International Conference on Machine Learning, 2019

Access Paper or Ask Questions

* NIPS 2018 camera-ready version

Access Paper or Ask Questions

Kernelized Hashcode Representations for Biomedical Relation Extraction

Oct 31, 2018
Sahil Garg, Aram Galstyan, Greg Ver Steeg, Irina Rish, Guillermo Cecchi, Shuyang Gao

* To appear in the proceedings of conference, AAAI-19

Access Paper or Ask Questions

Dialogue Modeling Via Hash Functions

Oct 18, 2018
Sahil Garg, Irina Rish, Guillermo Cecchi, Shuyang Gao, Palash Goyal, Sarik Ghazarian, Greg Ver Steeg, Aram Galstyan

* Presented at IJCAI-ICML 2018 Workshops. The paper is revised significantly with an addition of elaborate experimental analysis

Access Paper or Ask Questions

Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge

Sep 03, 2018
Ryan J. Gallagher, Kyle Reing, David Kale, Greg Ver Steeg

* Transactions of the Association for Computational Linguistics (TACL), Vol. 5, 2017
* 21 pages, 7 figures. 2018/09/03: Updated citation for HA/DR dataset

Access Paper or Ask Questions

Greg Ver Steeg

Fast Graph Learning with Unique Optimal Solutions

Improved Brain Age Estimation with Slice-based Set Networks

Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning

Likelihood Ratio Exponential Families

Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation

Annealed Importance Sampling with q-Paths

Compressing Deep Neural Networks via Layer Fusion

Robust Classification under Class-Dependent Domain Shift

All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference

Latent Embeddings of Point Process Excitations

Overview of Scanner Invariant Representations

Event Cartography: Latent Point Process Embeddings

Improving Generalization by Controlling Label-Noise Information in Neural Network Weights

Discovery and Separation of Features for Invariant Representation Learning

Invariant Representations through Adversarial Forgetting

Nearly-Unsupervised Hashcode Representations for Relation Extraction

Efficient Covariance Estimation from Temporal Data

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

MixHop: Higher-Order Graph Convolution Architectures via Sparsified Neighborhood Mixing

Exact Rate-Distortion in Autoencoders via Echo Noise

Scanner Invariant Representations for Diffusion MRI Harmonization

Identifying and Analyzing Cryptocurrency Manipulations in Social Media

Invariant Representations without Adversarial Training

Kernelized Hashcode Representations for Biomedical Relation Extraction

Dialogue Modeling Via Hash Functions

Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge