Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting

Multivariate time series is prevalent in many scientific and industrial domains. Modeling multivariate signals is challenging due to their long-range temporal dependencies and intricate interactions--both direct and indirect. To confront these complexities, we introduce a method of representing multivariate signals as nodes in a graph with edges indicating interdependency between them. Specifically, we leverage graph neural networks (GNN) and attention mechanisms to efficiently learn the underlying relationships within the time series data. Moreover, we suggest employing hierarchical signal decompositions running over the graphs to capture multiple spatial dependencies. The effectiveness of our proposed model is evaluated across various real-world benchmark datasets designed for long-term forecasting tasks. The results consistently showcase the superiority of our model, achieving an average 23\% reduction in mean squared error (MSE) compared to existing models.

Can We Utilize Pre-trained Language Models within Causal Discovery Algorithms?

Scaling laws have allowed Pre-trained Language Models (PLMs) into the field of causal reasoning. Causal reasoning of PLM relies solely on text-based descriptions, in contrast to causal discovery which aims to determine the causal relationships between variables utilizing data. Recently, there has been current research regarding a method that mimics causal discovery by aggregating the outcomes of repetitive causal reasoning, achieved through specifically designed prompts. It highlights the usefulness of PLMs in discovering cause and effect, which is often limited by a lack of data, especially when dealing with multiple variables. Conversely, the characteristics of PLMs which are that PLMs do not analyze data and they are highly dependent on prompt design leads to a crucial limitation for directly using PLMs in causal discovery. Accordingly, PLM-based causal reasoning deeply depends on the prompt design and carries out the risk of overconfidence and false predictions in determining causal relationships. In this paper, we empirically demonstrate the aforementioned limitations of PLM-based causal reasoning through experiments on physics-inspired synthetic data. Then, we propose a new framework that integrates prior knowledge obtained from PLM with a causal discovery algorithm. This is accomplished by initializing an adjacency matrix for causal discovery and incorporating regularization using prior knowledge. Our proposed framework not only demonstrates improved performance through the integration of PLM and causal discovery but also suggests how to leverage PLM-extracted prior knowledge with existing causal discovery algorithms.

Neural Volumetric Reconstruction for Coherent Synthetic Aperture Sonar

Synthetic aperture sonar (SAS) measures a scene from multiple views in order to increase the resolution of reconstructed imagery. Image reconstruction methods for SAS coherently combine measurements to focus acoustic energy onto the scene. However, image formation is typically under-constrained due to a limited number of measurements and bandlimited hardware, which limits the capabilities of existing reconstruction methods. To help meet these challenges, we design an analysis-by-synthesis optimization that leverages recent advances in neural rendering to perform coherent SAS imaging. Our optimization enables us to incorporate physics-based constraints and scene priors into the image formation process. We validate our method on simulation and experimental results captured in both air and water. We demonstrate both quantitatively and qualitatively that our method typically produces superior reconstructions than existing approaches. We share code and data for reproducibility.

IBL-NeRF: Image-Based Lighting Formulation of Neural Radiance Fields

We propose IBL-NeRF, which decomposes the neural radiance fields (NeRF) of large-scale indoor scenes into intrinsic components. Previous approaches for the inverse rendering of NeRF transform the implicit volume to fit the rendering pipeline of explicit geometry, and approximate the views of segmented, isolated objects with environment lighting. In contrast, our inverse rendering extends the original NeRF formulation to capture the spatial variation of lighting within the scene volume, in addition to surface properties. Specifically, the scenes of diverse materials are decomposed into intrinsic components for image-based rendering, namely, albedo, roughness, surface normal, irradiance, and prefiltered radiance. All of the components are inferred as neural images from MLP, which can model large-scale general scenes. By adopting the image-based formulation of NeRF, our approach inherits superior visual quality and multi-view consistency for synthesized images. We demonstrate the performance on scenes with complex object layouts and light configurations, which could not be processed in any of the previous works.

Classical-to-quantum convolutional neural network transfer learning

Machine learning using quantum convolutional neural networks (QCNNs) has demonstrated success in both quantum and classical data classification. In previous studies, QCNNs attained a higher classification accuracy than their classical counterparts under the same training conditions in the few-parameter regime. However, the general performance of large-scale quantum models is difficult to examine because of the limited size of quantum circuits, which can be reliably implemented in the near future. We propose transfer learning as an effective strategy for utilizing small QCNNs in the noisy intermediate-scale quantum era to the full extent. In the classical-to-quantum transfer learning framework, a QCNN can solve complex classification problems without requiring a large-scale quantum circuit by utilizing a pre-trained classical convolutional neural network (CNN). We perform numerical simulations of QCNN models with various sets of quantum convolution and pooling operations for MNIST data classification under transfer learning, in which a classical CNN is trained with Fashion-MNIST data. The results show that transfer learning from classical to quantum CNN performs considerably better than purely classical transfer learning models under similar training conditions.

Optimizing Large-Scale Fleet Management on a Road Network using Multi-Agent Deep Reinforcement Learning with Graph Neural Network

Optimizing fleet management is an important issue in ride-hailing service in terms of customer's satisfaction and increased revenue for drivers. However finding an optimal strategy in a real environment that demand and supply are changing in real time, is a challenging problem. In this paper, we try to solve this problem by using multi-agent reinforcement learning. Instead of grid which was used in existing works, we use a graph to represent road network more realistically. We model the problem using Markov game and adopt stochastic policy update which can resolve the problem of greedy policy update in multi-agent scheme. We use modified DQN to fit our problem. To approximate Q values on the graph, we use two basic graph neural networks, GCN and GAT. We design a simulator using real taxi call data and evaluate the algorithms under various conditions. The result demonstrates effectiveness of the proposed stochastic policy update model with graph neural network.