Arun Vignesh Malarkkan

Arun Vignesh Malarkkan

Ph.D. Candidate in Computer Science | AI Researcher
Advancing the frontiers of Causal Machine Learning, Reinforcement Learning, and Data-Centric AI. My work develops interpretable and robust AI systems, with a focus on applying causal reasoning to real-world challenges. Currently seeking opportunities as an Applied Scientist / ML Researcher to translate breakthrough methods into scalable AI solutions.
View Research Download CV

About Me

Translating complex data into reliable decisions with causally-informed machine learning.

I am currently a third year Computer Science Ph.D. Candidate at Arizona State University. I am working in the Knowledge Discovery and Data Mining (KDD) lab under the supervision of Dr. Yanjie Fu, specializing in Causal Machine Learning, Reinforcement Learning, Data-centric AI, and Reasoning strategies in LLMs.

Prior to my PhD, I completed my Master's in Computer Science from Arizona State University. I have extensive industry experience as a Senior Software Engineer at Fidelity Investments and Software Development Engineer at Amazon Alexa AI, where I led end-to-end ML solutions and voice-enabled purchase systems.

Currently, I'm a Doctoral Researcher at DOW Chemicals under the National Academy of Engineering (NAE) Frontiers of Engineering grant, developing causal-aware multi-agent reinforcement learning frameworks for AI-driven material science simulations. I am actively seeking Applied Scientist/Machine Learning Research Internship opportunities.

Outside research, I am also an avid photographer and a passionate programming teacher training young people who are excited about creative problem-solving.

7
Publications
20
Citations

Research Areas

Exploring the challenges of building robust and interpretable AI systems.

Causal Machine Learning

Developing causal graph learning frameworks for robust anomaly detection in cyber-physical systems. Focus on causal inference, structural divergence analysis, and multi-view causal graph fusion for interpretable AI solutions that understand cause-and-effect relationships in complex systems.

Multi-Agent Reinforcement Learning

Creating causally-guided automated feature engineering frameworks using multi-agent RL. Developing reward shaping strategies and causal-aware agents for improved interpretability and efficiency in material science simulations and complex decision-making tasks.

LLM Reasoning & Data-centric AI

Enhancing Large Language Model interpretability through probabilistic causal modeling on knowledge graphs. Advancing LLM reasoning capabilities and developing privacy-preserving generative data reprogramming techniques for robust and trustworthy AI systems.

Professional Experience

Industry experience in software development and real-time AI systems.

DOW Chemicals
Doctoral Researcher
June 2025 — Present

Research collaboration under National Academy of Engineering (NAE) Frontiers of Engineering grant. Developing causal-aware multi-agent reinforcement learning frameworks for AI-driven material science simulations and advancing computational models for materials discovery and optimization.

Fidelity Investments
Senior Software Engineer
January 2023 — June 2023

Tech-lead for developing end-to-end retirement goal financial projections. Orchestrated project retirement goal savings framework based on Monte Carlo simulations. Developed ensemble outlier detection tools to determine factors impacting projected savings goals.

Amazon Alexa AI
Software Development Engineer
June 2021 — January 2023

Implemented end-to-end voice (VUI) purchase flow for Skills requiring Parental Consents, enabling HIPAA compliance. Developed Purchase Likelihood Score model that drove the Alexa Purchase Recommender system, improving performance by 8% increase in Voice Skill purchases. Integrated localization module and designed voice-enabled promotional discounts for Alexa Skills.

ASU Decision Center
Data Scientist / Software Developer
June 2020 — May 2021

Developed outlier prediction models for financial plans, school populations, and infrastructure. Designed end-to-end ETL pipelines and AWS Lambdas for data ingestion and analysis. Implemented prediction models to optimize school resources and analyze graduation rate factors.

Publications

Recent contributions to Causal ML, Reinforcement Learning, and Data-centric AI research.

Published
Multi-view Causal Graph Fusion Based Anomaly Detection in Cyber-Physical Infrastructures
Arun Vignesh Malarkkan, D. Wang, Y. Fu
Proceedings of the 33rd ACM CIKM, pp. 4760-4767, 2024
ACM DL Cite
Accepted
DELTA: Privacy-Preserving Generative Data Reprogramming
Arun Vignesh Malarkkan, H. Bai, A. Kaushik, Y. Fu
Proceedings of the 25th IEEE International Conference on Data Mining, 2025
arXiv Cite
Accepted
Causal Graph Profiling via Structural Divergence for Robust Anomaly Detection in Cyber-Physical Systems
Arun Vignesh Malarkkan, H. Bai, D. Wang, Y. Fu
Proceedings of the 13th IEEE International Conference on Big Data, 2025
arXiv Cite
Accepted with Minor Revision
Incremental Causal Graph Learning for Online Cyberattack Detection in Cyber-Physical Infrastructures
Arun Vignesh Malarkkan, D. Wang, H. Bai, Y. Fu
Journal: IEEE Transactions on Big Data, 2025
arXiv Cite
Under Review - ICLR 2026
CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
Arun Vignesh Malarkkan, Y. Fu
Under Review — ICLR 2026
A Survey on Data-centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective
W. Ying, C. Wei, N. Gong, X. Wang, H. Bai, Arun Vignesh Malarkkan, S. Dong, D. Wang, D. Zhang, Y. Fu
arXiv preprint arXiv:2502.08828, 2025
arXiv Cite
Rethinking Spatio-temporal Anomaly Detection: A Vision for Causality-driven Cybersecurity
Arun Vignesh Malarkkan, H. Bai, X. Wang, A. Kaushik, D. Wang, Y. Fu
arXiv preprint arXiv:2507.08177, 2025
arXiv Cite
View on Google Scholar

Get in Touch

Open to research collaborations, internship opportunities, and academic discussions

Email

arun.malarkkan@asu.edu

Phone

(+1) 480-255-2954

Location

Arizona State University
School of Computing and Augmented Intelligence
Tempe, Arizona, USA

LinkedIn

linkedin.com/in/arunvignesh28

Seeking Opportunities

I am actively seeking Applied Scientist and Machine Learning Research Internship opportunities where I can apply my expertise in causal ML, reinforcement learning, and LLM reasoning to solve real-world challenges. Open to both industry and research lab positions.