Our unified treatment of SSL methods for GNNs sheds light on the similarities and differences of various methods, setting the stage for developing new methods and algorithms.
Here we develop a suite of comprehensive machine learning methods and tools spanning different computational models, molecular representations, and loss functions for molecular property prediction and drug discovery.
Self-supervised frameworks that learn denoising models with merely individual noisy images have shown strong capability and promising performance in various image denoising tasks.
In our task, saliency maps are used to assist the identification and visualization of developmental landmarks.
We evaluate CorDEL with extensive experiments conducted on both public benchmark datasets and a real-world dataset.
In this work, we introduce global voxel transformer networks (GVTNets), an advanced deep learning tool for augmented microscopy that overcomes intrinsic limitations of the current U-Net based models and achieves improved performance.
In addition, compared to existing graph pooling methods, second-order pooling is able to use information from all nodes and collect second-order statistics, making it more powerful.
Use of attention operators on high-order data requires flattening of the spatial or spatial-temporal dimensions into a vector, which is assumed to follow a multivariate normal distribution.
On the other hand, iCapsNets explore a novel way to explain the model's general behavior, achieving global interpretability.
In this work, we propose the non-local U-Nets, which are equipped with flexible global aggregation blocks, for biomedical image segmentation.
Compared to prior CNNs designed for mobile devices, ChannelNets achieve a significant reduction in terms of the number of parameters and computational cost without loss in accuracy.
Unlike existing models, which explore solutions by focusing on a block of cascaded dilated convolutional layers, our methods address the gridding artifacts by smoothing the dilated convolution itself.
However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations.
Ranked #2 on Document Classification on Cora
In this work, we propose spatial VAEs that use feature maps of larger size as latent variables to explicitly capture spatial information.
When used in image generation tasks, our PixelDCL can largely overcome the checkerboard problem suffered by regular deconvolution operations.
We also show that the text representation requirement in visual question answering is more complicated and comprehensive than that in conventional natural language processing tasks, making it a better task to evaluate textual representation methods.