@inproceedings{singh-etal-2025-mitigating,
    title = "Mitigating Forgetting in Continual Learning with Selective Gradient Projection",
    author = "Singh, Anika  and
      Martinez, David  and
      Dhaulakhandi, Aayush  and
      Chopade, Varun  and
      Malipati, Likhith  and
      Sharma, Vasu  and
      Zhu, Kevin  and
      Dev, Sunishchal  and
      Lagasse, Ryan",
    editor = "T.y.s.s, Santosh  and
      Shimizu, Shuichiro  and
      Gong, Yifan",
    booktitle = "The 14th International Joint Conference on Natural Language Processing and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-srw.25/",
    pages = "299--313",
    ISBN = "979-8-89176-304-3",
    abstract = "As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge when adapting to new tasks, resulting in severe performance degradation on earlier tasks. We propose Selective Forgetting-Aware Optimization (SFAO), a dynamic method that regulates gradient directions via cosine similarity and per-layer gating, enabling controlled forgetting while balancing plasticity and stability. SFAO selectively projects, accepts, or discards updates using a tunable mechanism with efficient Monte Carlo approximation. Experiments on standard continual learning benchmarks show that SFAO achieves competitive accuracy with markedly lower memory cost, a 90{\%} reduction, and improved forgetting on MNIST datasets, making it suitable for resource-constrained scenarios."
}