Related papers: Disentangling Neural Disjunctive Normal Form Model…

We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains. Realized by adversarial training with additional ability to exploit domain-specific…

Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated…

Deep neural networks (DNN) have an impressive ability to invert very complex models, i.e. to learn the generative parameters from a model's output. Once trained, the forward pass of a DNN is often much faster than traditional,…

Deep neural networks (DNNs) have been shown lack of robustness for the vulnerability of their classification to small perturbations on the inputs. This has led to safety concerns of applying DNNs to safety-critical domains. Several…

The graph neural network (GNN) has demonstrated its superior performance in various applications. The working mechanism behind it, however, remains mysterious. GNN models are designed to learn effective representations for graph-structured…

Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of multimedia data, including images, videos, and social networks. Nevertheless, in real-world scenarios,…

Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned,…

Although traditional symbolic reasoning methods are highly interpretable, their application in knowledge graph link prediction is limited due to their low computational efficiency. In this paper, we propose a new neural symbolic reasoning…

Compact neural networks are essential for affordable and power efficient deep learning solutions. Binary Neural Networks (BNNs) take compactification to the extreme by constraining both weights and activations to two levels, $\{+1, -1\}$.…

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high…

Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and…

Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization in a controllable manner remains an open…

One of the main motivations of MTL is to develop neural networks capable of inferring multiple tasks simultaneously. While countless methods have been proposed in the past decade investigating robust model architectures and efficient…

Abstract knowledge is deeply grounded in many computer-based applications. An important research area of Artificial Intelligence (AI) deals with the automatic derivation of knowledge from data. Machine learning offers the according…

Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based…

With the widespread applications of deep convolutional neural networks (DCNNs), it becomes increasingly important for DCNNs not only to make accurate predictions but also to explain how they make their decisions. In this work, we propose a…

Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks…

Deep neural networks exhibit limited generalizability across images with different entangled domain features and categorical features. Learning generalizable features that can form universal categorical decision boundaries across domains is…

Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on…

Supervised training of deep neural networks (DNNs) by noisy labels has been studied extensively in image classification but much less in image segmentation. Our understanding of the learning behavior of DNNs trained by noisy segmentation…