News

Presented at AAAI 2026 in Singapore

Event: AAAI-26: The 40th Annual AAAI Conference on Artificial Intelligence Venue: Singapore (Singapore EXPO). Date: 20–27 January 2026.

Publication

Does Cumulative Spectral Gradient work for KGs?

We extend the Cumulative Spectral Gradient (CSG) — a proposed dataset complexity metric — from images onto standard knowledge-graph link-prediction benchmarks and show that CSG is sensitive to parameter choices and does not reliably predict downstream ranking performance.

News

Presented two papers at IEEE BIGDATA 2025

Event: IEEE Big Data 2025 Focus Area: LLM-Enhanced Scientific and Graph Intelligence Location: Macau Affiliation: Universiti Brunei Darussalam — School...

Publication

MuCoS: Drug Target Discovery via Knowledge Graphs

We introduce MuCoS (*Multi-Context-Aware Sampling*), a novel approach that efficiently discovers drug targets by sampling diverse contextual neighborhoods in biomedical KGs. Our method significantly improves target identification accuracy while reducing computational overhead.

News

We win at the International Space Challenge 2025

Event: International Space Challenge (ISC) 2025 Programme: Expand Space Venue: Singapore Award: Merit Award — Advanced Category Institution: Universiti Brunei...

Publication

MuCo-KGC: Multi-Context-Aware Knowledge Graph Completion

We propose MuCo-KGC, a multi-context-aware approach that leverages diverse contextual signals to improve link prediction performance. Our method achieves state-of-the-art results on several benchmarks while maintaining computational efficiency.

Latest from the Lab

News

Presented at AAAI 2026 in Singapore

Presented at AAAI 2026 in Singapore

Event: AAAI-26: The 40th Annual AAAI Conference on Artificial Intelligence Venue: Singapore (Singapore EXPO). Date: 20–27 January 2026.

News

Presented two papers at IEEE BIGDATA 2025

Presented two papers at IEEE BIGDATA 2025

Event: IEEE Big Data 2025 Focus Area: LLM-Enhanced Scientific and Graph Intelligence Location: Macau Affiliation: Universiti Brunei Darussalam — School...

News

AI in Defence — From Awareness to Operational Advantage

AI in Defence — From Awareness to Operational Advantage

Event: Artificial Intelligence (AI) Education and Awareness Seminar Talk: AI in Defence — From Awareness to Operational Advantage Venue: SHHBIDSS...

News

We win at the International Space Challenge 2025

We win at the International Space Challenge 2025

Event: International Space Challenge (ISC) 2025 Programme: Expand Space Venue: Singapore Award: Merit Award — Advanced Category Institution: Universiti Brunei...

News

Visit to SUTD Robotics Lab

Visit to SUTD Robotics Lab

Event: Visit to Prof Rajesh’s robotics research lab at SUTD Venue: Singapore University of Technology and Design (SUTD) — robotics...

Publication

Similarity in object properties supports cross-situational word learning: Predictions from a dynamic neural model confirmed

Similarity in object properties supports cross-situational word learning: Predictions from a dynamic neural model confirmed

Context manipulations reveal that similarity in object properties can counterintuitively facilitate word learning. Using the WOLVES dynamic field model, we simulated CSWL under two conditions: 'NEAR' (objects metrically similar) and 'FAR' (objects distinct). WOLVES predicted superior learning in NEAR trials. An adult behavioral experiment confirmed this novel prediction, demonstrating that contextual similarity enhances cross‐situational word mapping.

Publication

Does Cumulative Spectral Gradient work for KGs?

 Does Cumulative Spectral Gradient work for KGs?

We extend the Cumulative Spectral Gradient (CSG) — a proposed dataset complexity metric — from images onto standard knowledge-graph link-prediction benchmarks and show that CSG is sensitive to parameter choices and does not reliably predict downstream ranking performance.

Publication

KG-EDAS: Evaluating Knowledge Graph Completion Models

KG-EDAS: Evaluating Knowledge Graph Completion Models

Current evaluation practices for knowledge graph completion models lack standardization and often fail to capture model capabilities comprehensively. We introduce KG-EDAS (Knowledge Graph Evaluation through Data-Aware Scoring), a meta-metric framework that provides more robust and interpretable evaluation of KGC models.

Publication

MuCo-KGC: Multi-Context-Aware Knowledge Graph Completion

MuCo-KGC: Multi-Context-Aware Knowledge Graph Completion

We propose MuCo-KGC, a multi-context-aware approach that leverages diverse contextual signals to improve link prediction performance. Our method achieves state-of-the-art results on several benchmarks while maintaining computational efficiency.

Publication

MuCoS: Drug Target Discovery via Knowledge Graphs

MuCoS: Drug Target Discovery via Knowledge Graphs

We introduce MuCoS (*Multi-Context-Aware Sampling*), a novel approach that efficiently discovers drug targets by sampling diverse contextual neighborhoods in biomedical KGs. Our method significantly improves target identification accuracy while reducing computational overhead.