On Provable Benefits of Depth in Training Graph Convolutional Networks W Cong, M Ramezani, M Mahdavi NeurIPS 34, 2021 | 69 | 2021 |
Predicting protein–ligand docking structure with graph neural network H Jiang, J Wang, W Cong, Y Huang, M Ramezani, A Sarma, ... Journal of chemical information and modeling 62 (12), 2923-2932, 2022 | 31 | 2022 |
GCN meets GPU: Decoupling "When to Sample" from "How to Sample". M Ramezani, W Cong, M Mahdavi, A Sivasubramaniam, MT Kandemir NeurIPS 33, 2020 | 31 | 2020 |
Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks M Ramezani, W Cong, M Mahdavi, M Kandemir, A Sivasubramaniam International Conference on Learning Representations (ICLR) 10, 2022 | 24 | 2022 |
On the importance of sampling in learning graph convolutional networks W Cong, M Ramezani, M Mahdavi arXiv preprint arXiv:2103.02696, 2021 | 12* | 2021 |
Exploring the impact of memory block permutation on performance of a crossbar ReRAM main memory M Ramezani, N Elyasi, M Arjomand, MT Kandemir, A Sivasubramaniam 2017 IEEE International Symposium on Workload Characterization (IISWC), 167-176, 2017 | 6 | 2017 |
CEDAR: Modeling impact of component error derating and read frequency on system-level vulnerability in high-performance processors H Asadi, A Haghdoost, M Ramezani, N Elyasi, A Baniasadi Microelectronics Reliability 54 (5), 1009-1021, 2014 | 1 | 2014 |
LiGNN: Graph Neural Networks at LinkedIn F Borisyuk, S He, Y Ouyang, M Ramezani, P Du, X Hou, C Jiang, ... arXiv preprint arXiv:2402.11139, 2024 | | 2024 |
Systems Optimizations for Learning and Processing on Large Scale Graphs M Ramezani The Pennsylvania State University, 2022 | | 2022 |
GraphGuess: Approximate Graph Processing System with Adaptive Correction M Ramezani, MT Kandemir, A Sivasubramaniam European Conference on Parallel Processing, 285-300, 2022 | | 2022 |