Deep Learning
Graph Neural Networks Do Not Always Oversmooth
However, GNNs suffer from the problem of over-smoothing, the property that features of all nodes exponentially converge to the same vector over layers, prohibiting the design of deep GNNs.
ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
This work was done during the internship at Microsoft Research Asia.
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
Specifically, we propose a multi-view masking strategy for addressing the challenges of endoscopic videos.
Sample-efficient Bayesian Optimisation Using Known Invariances Theodore Brown
Bayesian optimisation (BO) is a powerful framework for global optimisation of costly functions, using predictions from Gaussian process models (GPs).
5598cf1b2905a26ddb863e6705588327-Paper-Conference.pdf
Video understanding relies on accurate action detection for temporal analysis.
Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
Intelligent education stands as a prominent application of machine learning.
Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks
The operations and maintenance of satellite networks heavily depend on traffic measurements.
