Related papers: Grow-Prune-Freeze Networks: Adaptive & Continual L…

Graph Neural Networks (GNNs) have shown considerable effectiveness in a variety of graph learning tasks, particularly those based on the message-passing approach in recent years. However, their performance is often constrained by a limited…

Soft filter pruning~(SFP) has emerged as an effective pruning technique for allowing pruned filters to update and the opportunity for them to regrow to the network. However, this pruning strategy applies training and pruning in an…

Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform poorly on heterophilic graphs, where connected nodes have…

In recent years, prompt tuning has sparked a research surge in adapting pre-trained models. Unlike the unified pre-training strategy employed in the language field, the graph field exhibits diverse pre-training strategies, posing challenges…

Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \aka, graph flow model (GFM), has emerged due to its superior performance and flexible…

Feed-forward neural networks (NN) are a staple machine learning method widely used in many areas of science and technology. While even a single-hidden layer NN is a universal approximator, its expressive power is limited by the use of…

Network compression techniques have become increasingly important in recent years because the loads of Deep Neural Networks (DNNs) are heavy for edge devices in real-world applications. While many methods compress neural network parameters,…

We present the Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able to handle features distributed over a graph's nodes. This allows training graph neural networks with forward passes only,…

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential…

Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either flatten the native heterogeneous structure of power networks, target a limited set of grid…

Accurate localization is a critical requirement for most robotic tasks. The main body of existing work is focused on passive localization in which the motions of the robot are assumed given, abstracting from their influence on sampling…

Recent research has shown that graph neural networks (GNNs) can learn policies for locomotion control that are as effective as a typical multi-layer perceptron (MLP), with superior transfer and multi-task performance (Wang et al., 2018;…

Many robotic exploration algorithms rely on graph structures for frontier-based exploration and dynamic path planning. However, these graphs grow rapidly, accumulating redundant information and impacting performance. We present a…

Routing vessels through narrow and dynamic waterways is challenging due to changing environmental conditions and operational constraints. Existing vessel-routing studies typically fail to generalize across multiple origin-destination pairs…

Deep Convolutional Neural Networks~(CNNs) offer remarkable performance of classifications and regressions in many high-dimensional problems and have been widely utilized in real-word cognitive applications. However, high computational cost…

Plant phenotyping (Guo et al. 2021; Pieruschka et al. 2019) focuses on studying the diverse traits of plants related to the plants' growth. To be more specific, by accurately measuring the plant's anatomical, ontogenetical, physiological…

Continuous deep learning architectures enable learning of flexible probabilistic models for predictive modeling as neural ordinary differential equations (ODEs), and for generative modeling as continuous normalizing flows. In this work, we…

Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRDF) that generates high-quality and large-scale navigational…

Recently, graph prompt learning has garnered increasing attention in adapting pre-trained GNN models for downstream graph learning tasks. However, existing works generally conduct prompting over all graph elements (e.g., nodes, edges, node…