Related papers: NFCL: Simply interpretable neural networks for a s…

Sufficiently modeling the correlations among variables (aka channels) is crucial for achieving accurate multivariate time series forecasting (MTSF). In this paper, we propose a novel technique called Temporal Query (TQ) to more effectively…

Accurate short-term load forecasting is essential for the efficient operation of the power sector. Forecasting load at a fine granularity such as hourly loads of individual households is challenging due to higher volatility and inherent…

The inductive bias of a graph neural network (GNN) is largely encoded in its specified graph. Latent graph inference relies on latent geometric representations to dynamically rewire or infer a GNN's graph to maximize the GNN's predictive…

Tensors offer a natural representation for many kinds of data frequently encountered in machine learning. Images, for example, are naturally represented as third order tensors, where the modes correspond to height, width, and channels.…

Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and attributes predictions…

Real-world time-series data often exhibit non-stationarity, including changing trends, irregular seasonality, and residuals. In terms of changing trends, recently proposed multi-layer perceptron (MLP)-based models have shown excellent…

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…

Recently, deep learning has driven significant advancements in multivariate time series forecasting (MTSF) tasks. However, much of the current research in MTSF tends to evaluate models from a holistic perspective, which obscures the…

Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels in different layers. Processing each layer independently…

Deep learning and Convolutional Neural Networks (CNNs) have driven major transformations in diverse research areas. However, their limitations in handling low-frequency information present obstacles in certain tasks like interpreting global…

Acquiring an accurate world model online for model-based reinforcement learning (MBRL) is challenging due to data nonstationarity, which typically causes catastrophic forgetting for neural networks (NNs). From the online learning…

One of the key challenges of collaborative machine learning, without data sharing, is multimodal data heterogeneity in real-world settings. While Federated Learning (FL) enables model training across multiple clients, existing frameworks,…

Convolutional neural networks (CNN) have led to many state-of-the-art results spanning through various fields. However, a clear and profound theoretical understanding of the forward pass, the core algorithm of CNN, is still lacking. In…

Existing learning models often utilise CT-scan images to predict lung diseases. These models are posed by high uncertainties that affect lung segmentation and visual feature learning. We introduce MARL, a novel Multimodal Attentional…

Future wireless networks are expected to be AI-empowered, making their performance highly dependent on the quality of training datasets. However, physical-layer entities often observe only partial wireless environments characterized by…

Federated Learning (FL) has evolved as a promising technique to handle distributed machine learning across edge devices. A single neural network (NN) that optimises a global objective is generally learned in most work in FL, which could be…

Time series forecasting is a critical task that provides key information for decision-making. After traditional statistical and machine learning approaches, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs…

Federated Continual Learning (FCL) has emerged as a robust solution for collaborative model training in dynamic environments, where data samples are continuously generated and distributed across multiple devices. This survey provides a…

We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as ``black…

We propose a new neural network framework, termed Neural Network Machine Regression (NNMR), which integrates trainable input gating and adaptive depth regularization to jointly perform feature selection and function estimation in an…