4 papers
Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory
Saman Forouzandeh, Kamal Berahmand, Mahdi Jalili
Retrieving relevant observations from long multi-modal web interaction histories is challenging because relevance depends on the evolving task state, modality (screenshots, HTML te…
AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection
Kamal Berahmand, Saman Forouzandeh, Mehrnoush Mohammadi +2
Graph anomaly detection aims to identify abnormal patterns in networks, but faces significant challenges from label scarcity and extreme class imbalance. While graph contrastive le…
Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement
Saman Forouzandeh, Wei Peng, Parham Moradi +2
We present MACLA, a framework that decouples reasoning from learning by maintaining a frozen large language model while performing all adaptation in an external hierarchical proced…
Multiview graph dual-attention deep learning and contrastive learning for multi-criteria recommender systems
Saman Forouzandeh, Pavel N. Krivitsky, Rohitash Chandra
Recommender systems leveraging deep learning models have been crucial for assisting users in selecting items aligned with their preferences and interests. However, a significant ch…