publications

Includes peer-reviewed publications, preprints, and theses.

2020

  1. Equivariant Maps for Hierarchical Structures Wang, Renhao, Albooyeh, Marjan, and Ravanbakhsh, Siamak arXiv preprint arXiv:2006.03627 2020 [arXiv]
  2. Universal Equivariant Multilayer Perceptrons Ravanbakhsh, Siamak arXiv preprint arXiv:2002.02912 2020 [arXiv]
  3. Equivariant Entity-Relationship Networks arXiv preprint arXiv:1903.09033 2020 [arXiv] [code]
  4. Incidence Networks for Geometric Deep Learning Albooyeh, Marjan, Bertolini, Daniele, and Ravanbakhsh, Siamak arXiv preprint arXiv:1905.11460 2020 [arXiv]

2019

  1. Learning to predict the cosmological structure formation He, Siyu, Li, Yin, Feng, Yu, Ho, Shirley, Ravanbakhsh, Siamak, Chen, Wei, and Poczos, Barnabas Proceedings of the National Academy of Sciences 2019 [link] [ in the news ]
  2. Improved knowledge graph embedding using background taxonomic information Fatemi, Bahare, Ravanbakhsh, Siamak, and Poole, David In Proceedings of the AAAI Conference on Artificial Intelligence 2019
  3. LRP2020: Machine Learning Advantages in Canadian Astrophysics Venn, KA, Fabbro, S, Liu, A, Hezaveh, Y, Levasseur, L, Eadie, G, Ellison, S, Woo, J, Kavelaars, JJ, Yi, KM, and others, arXiv preprint arXiv:1910.00774 2019

2018

  1. Low-Dimensional Perturb-and-MAP Approach for Learning Restricted Boltzmann Machines Tomczak, Jakub M, Zaręba, Szymon, Ravanbakhsh, Siamak, and Greiner, Russell Neural Processing Letters 2018
  2. Deep Models of Interactions Across Sets Hartford, Jason, Graham, Devon, Leyton-Brown, Kevin, and Ravanbakhsh, Siamak In Proceedings of the 35th International Conference on Machine Learning 2018 [arXiv] [link] [code]
  3. Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector Singla, Sumedha, Gong, Mingming, Ravanbakhsh, Siamak, Sciurba, Frank, Poczos, Barnabas, and Batmanghelich, Kayhan N In International Conference on Medical Image Computing and Computer-Assisted Intervention 2018
  4. Analysis of Cosmic Microwave Background with Deep Learning He, Siyu, Ravanbakhsh, Siamak, and Ho, Shirley In International Conference on Learning Representations (ICLR), workshop track 2018 [link]
  5. CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding Lanusse, François, Ma, Quanbin, Li, Nan, Collett, Thomas E., Li, Chun-Liang, Ravanbakhsh, Siamak, Mandelbaum, Rachel, and Póczos, Barnabás Monthly Notices of the Royal Astronomical Society 2018 [arXiv] [link] [code] [ in the news ]

2017

  1. Deep Sets Zaheer, Manzil, Kottur, Satwik, Ravanbakhsh, Siamak, Poczos, Barnabas, Salakhutdinov, Ruslan R, and Smola, Alexander J In Advances in Neural Information Processing Systems 30 2017 [arXiv] [link] [supp] [code] oral presentation
  2. Min-Max Propagation Srinivasa, Christopher, Givoni, Inmar, Ravanbakhsh, Siamak, and Frey, Brendan J In Advances in Neural Information Processing Systems 30 2017 [link] [supp]
  3. Equivariance Through Parameter-Sharing Ravanbakhsh, Siamak, Schneider, Jeff, and Poczos, Barnabas In Proceedings of the 34th International Conference on Machine Learning 2017 [arXiv] [link]
  4. Enabling Dark Energy Science with Deep Generative Models of Galaxy Images Ravanbakhsh, Siamak, Lanusse, Francois, Mandelbaum, Rachel, Schneider, Jeff, and Poczos, Barnabas In Proceedings of the Thirty First AAAI Conference on Artificial Intelligence 2017 [arXiv] [link] [ in the news ]
  5. Deep Learning with Sets and Point Clouds Ravanbakhsh, Siamak, Schneider, Jeff, and Poczos, Barnabas In International Conference on Learning Representations (ICLR), workshop track 2017 [arXiv]

2016

  1. Survey Propagation beyond Constraint Satisfaction Problems Srinivasa, Christopher, Ravanbakhsh, Siamak, and Frey, Brendan In International Conference on Artificial Intelligence and Statistics 2016 [link] [supp] oral presentation (6.5% acceptance rate)
  2. Stochastic Neural Networks with Monotonic Activation Functions Ravanbakhsh, Siamak, Poczos, Barnabas, Schneider, Jeff, Schuurmans, Dale, and Greiner, Russell In International Conference on Artificial Intelligence and Statistics 2016 [link] oral presentation (6.5% acceptance rate)
  3. Boolean Matrix Factorization and Noisy Completion via Message Passing Ravanbakhsh, Siamak, Póczos, Barnabás, and Greiner, Russell In Proceedings of The 33rd International Conference on Machine Learning 2016 [link] [code]
  4. Estimating Cosmological Parameters from the Dark Matter Distribution Ravanbakhsh, Siamak, Oliva, Junier, Fromenteau, Sebastien, Price, Layne C, Ho, Shirley, Schneider, Jeff, and Póczos, Barnabás In Proceedings of The 33rd International Conference on Machine Learning 2016 [link]

2015

  1. Message passing and Combinatorial Optimization Ravanbakhsh, Siamak 2015 [pdf] [slides] [arXiv] faculty of science dissertation award and CS dept. outstanding thesis award runner-up
  2. Embedding Inference for Structured Multilabel Prediction Mirzazadeh, Farzaneh, Ravanbakhsh, Siamak, Ding, Nan, and Schuurmans, Dale 2015 [link]
  3. Perturbed Message Passing for Constraint Satisfaction Problems Ravanbakhsh, Siamak, and Greiner, Russell Journal of Machine Learning Research 2015 [link]
  4. Accurate, Fully-Automated NMR Spectral Profiling for Metabolomics Ravanbakhsh, Siamak, Liu, Philip, Bjordahl, Trent, Mandal, Rupasri, Grant, Jason, Wilson, Michael, Eisner, Roman, Sinelnikov, Igor, Hu, Xiaoyu, Luchinat, Claudio, Greiner, Russell, and Wishart, David PLoS ONE 2015 [arXiv] [link] [code] [ in the news ]

2014

  1. Augmentative Message Passing for Traveling Salesman Problem and Graph Partitioning Ravanbakhsh, Siamak, Rabbany, Reihaneh, and Greiner, Russell In Advances in Neural Information Processing Systems 2014 [link]
  2. Min-Max Problems on Factor Graphs Ravanbakhsh, Siamak, Srinivasa, Christopher, Frey, Brendan, and Greiner, Russell In Proceedings of the 31st International Conference on Machine Learning 2014 [link]
  3. Training Restricted Boltzmann Machine by Perturbation Ravanbakhsh, Siamak, Greiner, Russell, and Frey, Brendan In NIPS:workshop on perturbation, optimization and statistics 2014 [link]

2013

  1. Determination of the optimal tubulin isotype target as a method for the development of individualized cancer chemotherapy Ravanbakhsh, Siamak, Gajewski, Melissa, Greiner, Russell, and Tuszynski, Jack A Theoretical Biology and Medical Modelling 2013 [link]

2012

  1. A Generalized Loop Correction Method for Approximate Inference in Graphical Models Ravanbakhsh, Siamak, Yu, Chun-Nam, and Greiner, Russell In Proceedings of the 29th International Conference on Machine Learning 2012 [link]

2010

  1. A Cross Entropy Optimization Method for Partially Decomposable Problems Ravanbakhsh, Siamak, Poczos, Barnabas, and Greiner, Russ In Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence. Special Track on AI and Bioinformatics 2010 [link]