5 papers
FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection
Suprim Nakarmi, Chahana Dahal, Yue Zhao +2
Graph anomaly detection aims to identify graph structures (e.g., nodes, edges, or subgraphs) that deviate significantly from expected patterns, which supports critical applications…
TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG
Chahana Dahal, Zuobin Xiong
Production Retrieval Augmented Generation (RAG) systems rely on aggregating multiple external documents to answer complex queries. However, the retrieved documents introduce a new…
GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
Chahana Dahal, Ashutosh Balasubramaniam, Zuobin Xiong
Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and digest training data at scale, rai…
Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE
Abhijit Chakraborty, Chahana Dahal, Ashutosh Balasubramaniam +2
We revisit the efficacy of simple, real-valued embedding models for knowledge graph completion and introduce RelatE, an interpretable and modular method that efficiently integrates…
Federated Retrieval-Augmented Generation: A Systematic Mapping Study
Abhijit Chakraborty, Chahana Dahal, Vivek Gupta
Federated Retrieval-Augmented Generation (Federated RAG) combines Federated Learning (FL), which enables distributed model training without exposing raw data, with Retrieval-Augmen…