Heshan Devaka Fernando

12 papers A* 3C 1Misc 1Journal 7

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Mitigating Modality Imbalance in Multi-modal Learning via Multi-objective Optimization. CoRR Heshan Devaka Fernando, Parikshit Ram, Yi Zhou, Soham Dan, Horst Samulowitz, Nathalie Baracaldo, Tianyi Chen
2024	J	`jnl`	Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning. CoRR Heshan Devaka Fernando, Han Shen, Parikshit Ram, Yi Zhou, Horst Samulowitz, Nathalie Baracaldo, Tianyi Chen
2024	A*	`conf`	SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning. ICML Shuai Zhang, Heshan Devaka Fernando, Miao Liu, Keerthiram Murugesan, Songtao Lu, Pin-Yu Chen, Tianyi Chen, Meng Wang
2024	J	`jnl`	SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning. CoRR Shuai Zhang, Heshan Devaka Fernando, Miao Liu, Keerthiram Murugesan, Songtao Lu, Pin-Yu Chen, Tianyi Chen, Meng Wang
2024	J	`jnl`	Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance. J. Mach. Learn. Res. Lisha Chen, Heshan Devaka Fernando, Yiming Ying, Tianyi Chen
2024	Misc	`conf`	Variance Reduction Can Improve Trade-Off in Multi-Objective Learning. ICASSP Heshan Devaka Fernando, Lisha Chen, Songtao Lu, Pin-Yu Chen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Gaowen Liu, Meng Wang, Tianyi Chen
2023	A*	`conf`	Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach. ICLR Heshan Devaka Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen
2023	C	`conf`	On the Stability Analysis of Open Federated Learning Systems. ACC Youbang Sun, Heshan Devaka Fernando, Tianyi Chen, Shahin Shahrampour
2023	A*	`conf`	Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance. NeurIPS Lisha Chen, Heshan Devaka Fernando, Yiming Ying, Tianyi Chen
2023	J	`jnl`	Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance. CoRR Lisha Chen, Heshan Devaka Fernando, Yiming Ying, Tianyi Chen
2022	J	`jnl`	Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach. CoRR Heshan Devaka Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen
2022	J	`jnl`	On the Stability Analysis of Open Federated Learning Systems. CoRR Youbang Sun, Heshan Devaka Fernando, Tianyi Chen, Shahin Shahrampour