Parshin Shojaee | Virginia Tech

Biography

Hi! I’m a third-year PhD student in the Computer Science department at Virginia Tech, advised by Prof. Chandan Reddy. Prior to starting my PhD, I worked at Gilead Sciences as Data Scientist Intern. I completed my MS in Operations Research at Virginia Tech, and obtained my BS from Sharif University of Technology.

Research Interests

My primary research interests revolve around AI for Science and Engineering. Most of my works fall into one of these categories:

Deep Learning for Symbolic Mathematics, with a focus on uncovering mathematical expressions behind data (Neural Symbolic Regression)
Deep Learning for Code, with a focus on program synthesis and code translation
Deep Learning for Time Series, with a focus on sensor data fusion and forecasting

News

[May. 2024] I’m thrilled to start my internship at Adobe in this summer!
[Apr. 2024] New Preprint! Our LLM-SR paper on using LLMs for scientific equation discovery is released.
[Jan. 2024] Our SNIP (Symbolic-Numeric Pretraining) paper is accepted to ICLR 2024 as Spotlight!
[Dec. 2023] I will be at NeurIPS 2023, presenting our paper, “TPSR: Transformer-based Planning for Symbolic Regression”.
[Sep. 2023] Our TPSR paper on equation disocvery with transformers and planning is accepted to NeurIPS 2023!
[Jul. 2023] Our PPOCoder paper on code generation with deep RL is accepted to TMLR!
[Dec. 2022] Our GRAM-ODE paper on forecasting with graph ODEs is accepted to TMLR!

Publications

Preprint

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

Parshin Shojaee*, Kazem Meidani*, Shashank Gupta, Chandan K. Reddy, Amir Barati Farimani (*Equal Contribution)

Preprint.

PDF Code BibTex

ICLR

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training

Kazem Meidani*, Parshin Shojaee*, Chandan K. Reddy, Amir Barati Farimani (*Equal Contribution)

International Conference on Learning Representations (ICLR), 2024.

PDF Code BibTex Spotlight (top 5%)

NeurIPS

Transformer-based Planning for Symbolic Regression

Parshin Shojaee*, Kazem Meidani*, Amir Barati Farimani, Chandan K. Reddy (*Equal Contribution)

Advances in Neural Information Processing Systems (NeurIPS), 2023.

PDF Video Code BibTex

TMLR

Execution-based Code Generation using Deep Reinforcement Learning

Parshin Shojaee, Aneesh Jain, Sindhu Tipirneni, Chandan K. Reddy

Transactions on Machine Learning Research (TMLR), 2023.

PDF Video Code BibTex

TMLR

Graph-based Multi-ODE Neural Networks for Spatio-Temporal Traffic Forecasting

Zibo Liu, Parshin Shojaee, Chandan K. Reddy

Transactions on Machine Learning Research (TMLR), 2023.

PDF Video Code BibTex

Big Data

Task-Driven Privacy-Preserving Data-Sharing Framework for the Industrial Internet

Parshin Shojaee, Yingyan Zeng, Muntasir Wahed, Avi Seth, Ran Jin, Ismini Lourentzou

IEEE International Conference on Big Data (Big Data), 2022.

PDF BibTex

ICPS

Contextual Bandit Guided Data Farming for Deep Neural Networks in Manufacturing Industrial Internet

Yingyan Zeng, Parshin Shojaee, Syed Hasib Akhter Faruqui, Adel Alaeddini, Ran Jin

IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS), 2022.

PDF BibTex

ICPS

Deep Neural Network Pipelines for Multivariate Time Series Classification in Smart Manufacturing

Parshin Shojaee, Yingyan Zeng, Xiaoyu Chen, Ran Jin, Xinwei Deng, Chuck Zhang

IEEE 4th International Conference on Industrial Cyber-Physical Systems (ICPS), 2021.

PDF BibTex