← All publications Research thread · 3 papers · 2023–2025

Continual Learning

Keeping behavior classifiers current as topics, targets and languages drift, without forgetting what they already know.

  1. 2023

    Violence-Inducing Behavior Prevention in Social-Cyber Space

    Project design for multilingual, KB-augmented violence-inducing behavior detection

    SAIDD (Springer) · First author
  2. 2024

    Lifelong Learning Framework for Multilingual Hate Speech Detection in Social Media Streams

    Replay-memory lifelong learning over topic×language task stream; best on 7/10 tasks

    SBP-BRiMS · First author
  3. 2025

    Knowledge-guided Continual Learning for Behavioral Analytics Systems

    Wiktionary-KG augmentation of replay nearly eliminates forgetting (HateXplain acc 16.7→46.7)

    IEEE CogMI · First author