Heshan Devaka Fernando

According to our database, Heshan Devaka Fernando authored at least 8 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Mitigating Modality Imbalance in Multi-modal Learning via Multi-objective Optimization.

Heshan Devaka Fernando, Parikshit Ram, Yi Zhou, Soham Dan, Horst Samulowitz, Nathalie Baracaldo, Tianyi Chen

CoRR, November, 2025

2024

Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning.

Heshan Devaka Fernando, Han Shen, Parikshit Ram, Yi Zhou, Horst Samulowitz, Nathalie Baracaldo, Tianyi Chen

CoRR, 2024

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning.

Shuai Zhang, Heshan Devaka Fernando, Miao Liu, Keerthiram Murugesan, Songtao Lu, Pin-Yu Chen, Tianyi Chen, Meng Wang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Variance Reduction Can Improve Trade-Off in Multi-Objective Learning.

Heshan Devaka Fernando, Lisha Chen, Songtao Lu, Pin-Yu Chen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Gaowen Liu, Meng Wang, Tianyi Chen

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance.

Lisha Chen, Heshan Devaka Fernando, Yiming Ying, Tianyi Chen

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach.

Heshan Devaka Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen

Proceedings of the Eleventh International Conference on Learning Representations, 2023

On the Stability Analysis of Open Federated Learning Systems.

Youbang Sun, Heshan Devaka Fernando, Tianyi Chen, Shahin Shahrampour

Proceedings of the American Control Conference, 2023

2022

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach.

Heshan Devaka Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen

CoRR, 2022