Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
Proceedings of the 41st International Conference on Machine Learning (ICML), PMLR 235:20768–20792.
Publications
Publications
This page lists peer-reviewed papers and preprints in graph transformers, molecular representation learning, efficient attention, signal processing, and electronic devices.
Peer-reviewed publications
Conference Papers
-
2024
-
2023
The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 810–821.
-
2022
Global Self-Attention as a Replacement for Graph Convolution
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 655–665.
-
2019
Identification of Autoregressive Systems in the Presence of Additive Noise Using the Matrix Pencil Method
2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), pp. 1–6.
-
2017
A fast double-talk detection algorithm based on signal envelopes for implementation of acoustic echo cancellation in embedded systems
2017 4th International Conference on Advances in Electrical Engineering (ICAEE), pp. 199–204.
Preprints
Earlier Research
-
2018
SwishNet: A Fast Convolutional Neural Network for Speech, Music and Noise Classification and Segmentation
arXiv preprint.
-
2018
Breast Lesion Classification from Bi-Modal Ultrasound Images by Deep CNN Using Transfer and Multi-Task Learning
Preprint.
-
2017
An Improved Physics Based Numerical Model of Tunnel FET Using 2D NEGF Formalism
arXiv preprint.
Academic service
Peer Review
Reviewer for Data Mining and Knowledge Discovery (2025), IEEE Transactions on Neural Networks and Learning Systems (2023), and IEEE Transactions on Big Data (2023).