Hansi Kalpana Yasodara Paththini Hetti Arachchige
M.S. FinalFeb 27, 2026, 12:30 pm - 2:30 pm
LSC384 and Teams
Graph Feature Engineering and Coordinate-Based Learning for Transferable and Energy-Efficient Artificial Intelligence
Abstract: A comprehensive framework for efficient and scalable graph representation learning is presented, emphasizing coordinate-based and explicit structural methods. The research addresses the limitations of Graph Neural Networks (GNNs) in resource-constrained environments, including edge devices and large-scale deployments, by developing lightweight, non-neural alternatives.
The first contribution is the Network Feature Embedding (NFE) pipeline, which integrates diffusion-based, positional, and structural descriptors into a unified representation for node classification. The second contribution is the Topology Coordinate-Driven Random Forests (TC-DRF) framework, which combines anchor-based topology coordinates with Random Forest classifiers for graph-level learning and cross-dataset transfer.
Extensive evaluations of NFE and TC-DRF on vision, molecular, and social graph benchmarks demonstrate competitive predictive performance while substantially reducing computational overhead, memory footprint, and energy consumption. The proposed frameworks enable zero-shot cross-dataset transfer, maintain robustness under class imbalance, and support practical deployment in Green AI settings. Edge-device experiments, including deployment on Raspberry Pi hardware, confirm sub-millisecond inference latency and ultra-low energy usage.
This research challenges the prevailing reliance on deep message-passing architectures for graph learning, demonstrating that explicit structural representations coupled with lightweight models provide viable, interpretable, and resource-efficient alternatives. The findings contribute to the advancement of scalable and sustainable graph learning methodologies and establish a foundation for future work in structural embeddings, dynamic graph analysis, and hybrid structural-attribute learning models.
The first contribution is the Network Feature Embedding (NFE) pipeline, which integrates diffusion-based, positional, and structural descriptors into a unified representation for node classification. The second contribution is the Topology Coordinate-Driven Random Forests (TC-DRF) framework, which combines anchor-based topology coordinates with Random Forest classifiers for graph-level learning and cross-dataset transfer.
Extensive evaluations of NFE and TC-DRF on vision, molecular, and social graph benchmarks demonstrate competitive predictive performance while substantially reducing computational overhead, memory footprint, and energy consumption. The proposed frameworks enable zero-shot cross-dataset transfer, maintain robustness under class imbalance, and support practical deployment in Green AI settings. Edge-device experiments, including deployment on Raspberry Pi hardware, confirm sub-millisecond inference latency and ultra-low energy usage.
This research challenges the prevailing reliance on deep message-passing architectures for graph learning, demonstrating that explicit structural representations coupled with lightweight models provide viable, interpretable, and resource-efficient alternatives. The findings contribute to the advancement of scalable and sustainable graph learning methodologies and establish a foundation for future work in structural embeddings, dynamic graph analysis, and hybrid structural-attribute learning models.
Adviser: Prof. Anura Jayasumana
Co-Adviser: N/A
Non-ECE Member: Prof. Indrakshi Ray, CS
Member 3: Prof. Sudeep Pasricha, ECE
Addional Members: N/A
Co-Adviser: N/A
Non-ECE Member: Prof. Indrakshi Ray, CS
Member 3: Prof. Sudeep Pasricha, ECE
Addional Members: N/A
Publications:
Graph Feature Engineering and Embedding for Artificial Intelligence of Thing, Proc. IEEE Annual Congress on Artificial Intelligence of Things (IEEE AIoT),
Osaka, Japan, Dec 2025
Coordinate-Driven Random Forests – A Transferable Approach for Graph Data – under review.
Graph Feature Engineering and Embedding for Artificial Intelligence of Thing, Proc. IEEE Annual Congress on Artificial Intelligence of Things (IEEE AIoT),
Osaka, Japan, Dec 2025
Coordinate-Driven Random Forests – A Transferable Approach for Graph Data – under review.
Program of Study:
ECE561
ECE452
CS445
ECE528
ECE514
ECE512
N/A
N/A
ECE561
ECE452
CS445
ECE528
ECE514
ECE512
N/A
N/A