Related papers: Propagation with Adaptive Mask then Training for N…

We introduce the Normalized Matching Transformer (NMT), a deep learning approach for efficient and accurate sparse semantic keypoint matching between image pairs. NMT consists of a strong visual backbone, geometric feature refinement via…

Learning rotation-invariant distinctive features is a fundamental requirement for point cloud registration. Existing methods often use rotation-sensitive networks to extract features, while employing rotation augmentation to learn an…

Graph Convolutional Networks (GCNs) are powerful models for node representation learning tasks. However, the node representation in existing GCN models is usually generated by performing recursive neighborhood aggregation across multiple…

Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or…

Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation. In this paper, we present a…

Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features. This gave rise to extensive work in geometric deep learning, focusing on designing network architectures that…

Graph convolutional network (GCN) is generalization of convolutional neural network (CNN) to work with arbitrarily structured graphs. A binary adjacency matrix is commonly used in training a GCN. Recently, the attention mechanism allows the…

Attributed network embedding has attracted plenty of interest in recent years. It aims to learn task-independent, low-dimensional, and continuous vectors for nodes preserving both topology and attribute information. Most of the existing…

In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained with additional…

Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification…

The $q$-parameterized magnetic Laplacian serves as the foundation of directed graph (digraph) convolution, enabling this kind of digraph neural network (MagDG) to encode node features and structural insights by complex-domain message…

The combination of the traditional convolutional network (i.e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph…

The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources.…

We propose an extension to the transformer neural network architecture for general-purpose graph learning by adding a dedicated pathway for pairwise structural information, called edge channels. The resultant framework - which we call…

Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. In order to reduce this cost, several quantization schemes have gained attention recently with some focusing on weight…

Heterogeneous information network (HIN) embedding, aiming to map the structure and semantic information in a HIN to distributed representations, has drawn considerable research attention. Graph neural networks for HIN embeddings typically…

We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is less explored in…

Masked Graph Auto-Encoder, a powerful graph self-supervised training paradigm, has recently shown superior performance in graph representation learning. Existing works typically rely on node contextual information to recover the masked…

When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relative position encoding, achieves this by upweighting or…

Neural Architecture Search (NAS) methods have shown to output networks that largely outperform human-designed networks. However, conventional NAS methods have mostly tackled the single dataset scenario, incuring in a large computational…