Related papers: Derivative-informed Graph Convolutional Autoencode…
This paper introduces a promising alternative method for training Generative Adversarial Networks (GANs) on large-scale datasets with clear theoretical guarantees. GANs are typically learned through a minimax game between a generator and a…
Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level…
We study the challenging problem for inference tasks on large-scale graph datasets of Graph Neural Networks: huge time and memory consumption, and try to overcome it by reducing reliance on graph structure. Even though distilling graph…
The Transformer translation model employs residual connection and layer normalization to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. Previous research shows that even with residual connection and…
The identification of $\gamma$-rays from the predominant hadronic-background is a key aspect in their ground-based detection using Imaging Atmospheric Cherenkov Telescopes (IACTs). While current methods are limited in their ability to…
Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism,…
We present a novel descriptor, called deep self-convolutional activations (DeSCA), designed for establishing dense correspondences between images taken under different imaging modalities, such as different spectral ranges or lighting…
The 2-dimensional Ising model on a square lattice is investigated with a variational autoencoder in the non-vanishing field case for the purpose of extracting the crossover region between the ferromagnetic and paramagnetic phases. The…
The emergent dynamics in spacetime diagrams of cellular automata (CAs) is often organised by means of a number of behavioural classes. Whilst classification of elementary CAs is feasible and well-studied, non-elementary CAs are generally…
We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality…
Traditional discrete learning methods involve discretizing continuous equations using difference schemes, necessitating considerations of stability and convergence. Integrable nonlinear lattice equations possess a profound mathematical…
Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of…
Liquid-based cytology (LBC) is a reliable automated technique for the screening of Papanicolaou (Pap) smear data. It is an effective technique for collecting a majority of the cervical cells and aiding cytopathologists in locating abnormal…
Most existing graph neural networks (GNNs) are limited to undirected graphs, whose restricted scope of the captured relational information hinders their expressive capabilities and deployments in real-world scenarios. Compared with…
Kontsevich's formality theorem and the consequent star-product formula rely on the construction of an $L_\infty$-morphism between the DGLA of polyvector fields and the DGLA of polydifferential operators. This construction uses a version of…
Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number…
We propose the Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution. Relying on the tridiagonal decomposition of the Lanczos algorithm, we not only…
Sparse knowledge graph (KG) scenarios pose a challenge for previous Knowledge Graph Completion (KGC) methods, that is, the completion performance decreases rapidly with the increase of graph sparsity. This problem is also exacerbated…
Ptychography is a computational method of microscopy that recovers high-resolution transmission images of samples from a series of diffraction patterns. While conventional phase retrieval algorithms can iteratively recover the images, they…
Graph convolutional network (GCN) has become popular in various natural language processing (NLP) tasks with its superiority in long-term and non-consecutive word interactions. However, existing single-hop graph reasoning in GCN may miss…