Related papers: United We Stand, Divided We Fall: UnityGraph for U…

Graph-level representation learning is the pivotal step for downstream tasks that operate on the whole graph. The most common approach to this problem heretofore is graph pooling, where node features are typically averaged or summed to…

Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data. Meanwhile, most existing representation learning methods embed the heterogeneous…

While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging…

We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is…

As the performance of computer systems stagnates due to the end of Moore's Law, there is a need for new models that can understand and optimize the execution of general purpose code. While there is a growing body of work on using Graph…

Graph Representation Learning (GRL) methods opened new avenues for addressing complex, real-world problems represented by graphs. However, many graphs used in these applications comprise millions of nodes and billions of edges and are…

Subgraph-based graph representation learning (SGRL) has been recently proposed to deal with some fundamental challenges encountered by canonical graph neural networks (GNNs), and has demonstrated advantages in many important data science…

In this paper we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position per object. Our method relies on a Graph Neural Network…

Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes. While the advent of graph neural networks and self-supervised…

Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph…

Human actions are typically of combinatorial structures or patterns, i.e., subjects, objects, plus spatio-temporal interactions in between. Discovering such structures is therefore a rewarding way to reason about the dynamics of…

Graph embeddings are low dimensional representations of nodes, edges or whole graphs. Such representations allow for data in a network format to be used along with machine learning models for a variety of tasks (e.g., node classification),…

Code embedding is a keystone in the application of machine learning on several Software Engineering (SE) tasks. To effectively support a plethora of SE tasks, the embedding needs to capture program syntax and semantics in a way that is…

Graph learning has become essential in various domains, including recommendation systems and social network analysis. Graph Neural Networks (GNNs) have emerged as promising techniques for encoding structural information and improving…

Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic…

In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters. In our framework, successive operations in a clustering algorithm are expressed as steps in a recurrent…

Autonomous driving (AD) systems struggle in long-tail scenarios due to limited world knowledge and weak visual dynamic modeling. Existing vision-language-action (VLA)-based methods cannot leverage unlabeled videos for visual causal…

Self-supervised heterogeneous graph learning (SHGL) has shown promising potential in diverse scenarios. However, while existing SHGL methods share a similar essential with clustering approaches, they encounter two significant limitations:…

Recently, Graph Neural Network (GNN) has achieved remarkable success in various real-world problems on graph data. However in most industries, data exists in the form of isolated islands and the data privacy and security is also an…

Here we study the problem of matched record clustering in unsupervised entity resolution. We build upon a state-of-the-art probabilistic framework named the Data Washing Machine (DWM). We introduce a graph-based hierarchical 2-step record…