Related papers: Tao: A Learning Framework for Adaptive Nearest Nei…

Traffic forecasting is one canonical example of spatial-temporal learning task in Intelligent Traffic System. Existing approaches capture spatial dependency with a pre-determined matrix in graph convolution neural operators. However, the…

Capturing long-range dependencies in feature representations is crucial for many visual recognition tasks. Despite recent successes of deep convolutional networks, it remains challenging to model non-local context relations between visual…

Approximate nearest neighbor (ANN) search in high-dimensional metric spaces is a fundamental problem with many applications. Over the past decade, proximity graph (PG)-based indexes have demonstrated superior empirical performance over…

Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such…

The deep neural network (DNN) based AI applications on the edge require both low-cost computing platforms and high-quality services. However, the limited memory, computing resources, and power budget of the edge devices constrain the…

Through deep learning and computer vision techniques, driving manoeuvres can be predicted accurately a few seconds in advance. Even though adapting a learned model to new drivers and different vehicles is key for robust driver-assistance…

Approximate Nearest Neighbor Search (ANNS) is a critical component of modern AI systems, such as recommendation engines and retrieval-augmented large language models (RAG-LLMs). However, scaling ANNS to billion-entry datasets exposes…

This paper develops an adaptive observation-based efficient reinforcement learning (RL) approach for systems with uncertain drift dynamics. A novel concurrent learning adaptive extended observer (CL-AEO) is first designed to jointly…

High quality AI solutions require joint optimization of AI algorithms and their hardware implementations. In this work, we are the first to propose a fully simultaneous, efficient differentiable DNN architecture and implementation co-search…

A hybrid approach, incorporating concepts of nonlinear dynamics in artificial neural networks (ANN), is proposed to model time series generated by complex dynamic systems. We introduce well known features used in the study of dynamic…

In this paper, we propose an end-to-end graph learning framework, namely Deep Iterative and Adaptive Learning for Graph Neural Networks (DIAL-GNN), for jointly learning the graph structure and graph embeddings simultaneously. We first cast…

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization…

Deep convolutional neural networks (CNNs) have been widely used in surface defect detection. However, no CNN architecture is suitable for all detection tasks and designing effective task-specific requires considerable effort. The neural…

A common problem in training neural networks is the vanishing and/or exploding gradient problem which is more prominently seen in training of Recurrent Neural Networks (RNNs). Thus several algorithms have been proposed for training RNNs.…

Graph Neural Networks (GNNs) have demonstrated significant success in graph learning and are widely adopted across various critical domains. However, the irregular connectivity between vertices leads to inefficient neighbor aggregation,…

Expandable networks have demonstrated their advantages in dealing with catastrophic forgetting problem in incremental learning. Considering that different tasks may need different structures, recent methods design dynamic structures adapted…

Graph-based approaches to nearest neighbor search are popular and powerful tools for handling large datasets in practice, but they have limited theoretical guarantees. We study the worst-case performance of recent graph-based approximate…

Adaptive user interfaces adapt their contents, presentation, or behavior mostly in a sudden, fluctuating, and abrupt way, which may cause negative effects on the end users, such as cognitive disruption. Instead, adaptivity should be…

The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging. In typical bioacoustics applications, manually labelling the required amount of data can be prohibitively expensive. To…

Recent years have witnessed the popularity and success of graph neural networks (GNN) in various scenarios. To obtain data-specific GNN architectures, researchers turn to neural architecture search (NAS), which has made impressive success…