相关论文: CHAIN: Concept-harmonized Hierarchical Inference I…

Fault detection and diagnosis is significant for reducing maintenance costs and improving health and safety in chemical processes. Convolution neural network (CNN) is a popular deep learning algorithm with many successful applications in…

Nonlinear system identification often involves a fundamental trade-off between interpretability and flexibility, often requiring the incorporation of physical constraints. We propose a unified data-driven framework that combines the…

Heterogeneous information networks (HINs) are ubiquitous in real-world applications. In the meantime, network embedding has emerged as a convenient tool to mine and learn from networked data. As a result, it is of interest to develop HIN…

Humans are able to recognize structured relations in observation, allowing us to decompose complex scenes into simpler parts and abstract the visual world in multiple levels. However, such hierarchical reasoning ability of human perception…

With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While…

Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification.…

Traditional deep learning interpretability methods which are suitable for model users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations…

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of…

Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves…

Object detection in challenging situations such as scale variation, occlusion, and truncation depends not only on feature details but also on contextual information. Most previous networks emphasize too much on detailed feature extraction…

Attributed network embedding aims to learn low-dimensional vector representations for nodes in a network, where each node contains rich attributes/features describing node content. Because network topology structure and node attributes…

The capabilities and adoption of deep neural networks (DNNs) grow at an exhilarating pace: Vision models accurately classify human actions in videos and identify cancerous tissue in medical scans as precisely than human experts; large…

Heterogeneous information networks (HINs) have been extensively applied to real-world tasks, such as recommendation systems, social networks, and citation networks. While existing HIN representation learning methods can effectively learn…

Explaining decisions made by deep neural networks is a rapidly advancing research topic. In recent years, several approaches have attempted to provide visual explanations of decisions made by neural networks designed for structured 2D image…

Although concept-based models promise interpretability by explaining predictions with human-understandable concepts, they typically rely on exhaustive annotations and treat concepts as flat and independent. To circumvent this, recent work…

Deep convolutional neural networks (CNNs) trained on objects and scenes have shown intriguing ability to predict some response properties of visual cortical neurons. However, the factors and computations that give rise to such ability, and…

Video-and-Language Inference is a recently proposed task for joint video-and-language understanding. This new task requires a model to draw inference on whether a natural language statement entails or contradicts a given video clip. In this…

Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability. While recent developments in explainable artificial intelligence attempt…

Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…

Harmonizing the analysis of data, especially of 3-D image volumes, consisting of different number of slices and annotated per volume, is a significant problem in training and using deep neural networks in various applications, including…