Search Results for author:
Found 10 papers, 3 papers with code
Masked Attention is All You Need for Graphs
Graph neural networks (GNNs) and variations of the message passing algorithm are the predominant means for learning on graphs, largely due to their flexibility, speed, and satisfactory performance.
Improving Antibody Humanness Prediction using Patent Data
We investigate the potential of patent data for improving the antibody humanness prediction using a multi-stage, multi-loss training process.
Graph Neural Networks with Adaptive Readouts
We argue that in some problems such as binding affinity prediction where molecules are typically presented in a canonical form it might be possible to relax the constraints on permutation invariance of the hypothesis space and learn a more effective model of the affinity by employing an adaptive readout function.
Towards Robust Waveform-Based Acoustic Models
We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions.
Learning Waveform-Based Acoustic Models using Deep Variational Convolutional Neural Networks
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models.
Scalable Learning in Reproducing Kernel Krein Spaces
We provide the first mathematically complete derivation of the Nystr\"om method for low-rank approximation of indefinite kernels and propose an efficient method for finding an approximate eigendecomposition of such kernel matrices.
Learning in Reproducing Kernel Kreı̆n Spaces
We formulate a novel regularized risk minimization problem for learning in reproducing kernel Kre{ı̆}n spaces and show that the strong representer theorem applies to it.
Towards A Unified Analysis of Random Fourier Features
We study both the standard random Fourier features method for which we improve the existing bounds on the number of features required to guarantee the corresponding minimax risk convergence rate of kernel ridge regression, as well as a data-dependent modification which samples features proportional to \emph{ridge leverage scores} and further reduces the required number of features.
Nyström Method with Kernel K-means++ Samples as Landmarks
We investigate, theoretically and empirically, the effectiveness of kernel K-means++ samples as landmarks in the Nyström method for low-rank approximation of kernel matrices.
