Related papers: A Structure-Aware Framework for Learning Device Pl…

Directed acyclic graphs (DAGs) are commonly used to model causal relationships among random variables. In general, learning the DAG structure is both computationally and statistically challenging. Moreover, without additional information,…

There has been a surge of recent interest in learning representations for graph-structured data. Graph representation learning methods have generally fallen into three main categories, based on the availability of labeled data. The first,…

Modern AI systems often comprise multiple learnable components that can be naturally organized as graphs. A central challenge is the end-to-end training of such systems without restrictive architectural or training assumptions. Such tasks…

Leveraging labelled data from multiple domains to enable prediction in another domain without labels is a significant, yet challenging problem. To address this problem, we introduce the framework DAPDAG (\textbf{D}omain \textbf{A}daptation…

There has been a growing interest in causal learning in recent years. Commonly used representations of causal structures, including Bayesian networks and structural equation models (SEM), take the form of directed acyclic graphs (DAGs). We…

A well-studied challenge that arises in the structure learning problem of causal directed acyclic graphs (DAG) is that using observational data, one can only learn the graph up to a "Markov equivalence class" (MEC). The remaining undirected…

Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architecture search. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural…

Edge computing is naturally suited to the applications generated by Internet of Things (IoT) nodes. The IoT applications generally take the form of directed acyclic graphs (DAGs), where vertices represent interdependent functions and edges…

Understanding the causal relationships between data variables can provide crucial insights into the construction of tabular datasets. Most existing causality learning methods typically focus on applying a single identifiable causal model,…

Current Physical AI (PAI) relies heavily on closed-loop visual-servoing pipelines, whose perception and planning stages may become computationally intensive onboard due to complex models embedded on robots. In practice, offloading the…

Due to their high computational efficiency on a continuous space, gradient optimization methods have shown great potential in the neural architecture search (NAS) domain. The mapping of network representation from the discrete space to a…

We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data. Our approach optimizes over the polytope of permutation vectors, the so-called Permutahedron, to learn a…

To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server. However, due to the consideration of privacy protection, data owners gradually refuse to share their personalized raw…

In recent years, the prevalent online services generate a sheer volume of user activity data. Service providers collect these data in order to perform client behavior analysis, and offer better and more customized services. Majority of…

We consider supervised learning problems where the features are embedded in a graph, such as gene expressions in a gene network. In this context, it is of much interest to automatically select a subgraph with few connected components; by…

Ubiquitous artificial intelligence (AI) is considered one of the key services in 6G systems. AI services typically rely on deep neural network (DNN) requiring heavy computation. Hence, in order to support ubiquitous AI, it is crucial to…

The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented by graphs. However,…

Many state-of-the-art Deep Neural Networks (DNNs) have substantial memory requirements. Limited device memory becomes a bottleneck when training those models. We propose ParDNN, an automatic, generic, and non-intrusive partitioning strategy…

Graph embedding maps graph nodes to low-dimensional vectors, and is widely adopted in machine learning tasks. The increasing availability of billion-edge graphs underscores the importance of learning efficient and effective embeddings on…

Graph embedding is a transformation of nodes of a network into a set of vectors. A good embedding should capture the underlying graph topology and structure, node-to-node relationship, and other relevant information about the graph, its…