Browse Proceedings

Recently, solving partial differential equations (PDEs) using neural networks (NNs) has been attracting increasing interests with promising potential to be applied in wide areas. In this paper, we propose a theoretical model that approximates the ...

Meta-learning aims to learn models that can make quick adaptations to new tasks. However, due to the lack of data, the further improvement of meta-learning can be severely constrained. Since, data augmentation has been a commonly used method to ...

Tacit commitments have been widely seen as a crucial underpinning for real-world cooperation. Similarly, it could also be a key to multi-agent cooperation. This paper proposes a novel tacit commitment emergence multi-agent reinforcement learning (...

Eye tracking has become an increasingly important technology in many fields of research, such as marketing, human computer interaction, psychology, and also in human cognition. Understanding the human eye movements, while viewing specific ...

Recently, multi-view attributed graph clustering has attracted lots of attention with the explosion of graph-structured data. Existing methods are primarily designed for the form in which every graph has its attributes. We argue that a more ...

Adversarial training is validated to be the most effective method to defend against adversarial attacks. In adversarial training, stronger capacity networks can achieve higher robustness. Mutual learning is plugged into adversarial training to ...${}_{}$

Policy-based methods like MAPPO have exhibited amazing results in diverse test scenarios in multi-agent reinforcement learning. Nevertheless, current actor-critic algorithms do not fully leverage the benefits of the centralized training with ...

Network pruning is a technique to obtain a smaller lightweight model by removing the redundant structure from pre-trained models. However, existing methods are mainly based on the importance of filters in the whole network. Unlike previous methods,...$$$$$$$$$$

Knowledge distillation is a commonly used method for model compression, aims to compress a powerful yet cumbersome model into a lightweight model without much sacrifice of performance, giving the accuracy of a lightweight model close to that of ...

In recent years, machine translation has made great progress with the rapid development of deep learning. However, there still exists a problem of catastrophic forgetting in the field of neural machine translation, namely, a decrease in overall ...

In few-shot learning tasks, a series of semantic-based methods have shown excellent performance due to the modality fusion of both visual and semantic modalities. However, in single-shot learning tasks, the fused visual modality fails to ...

Unsupervised domain adaptation methods utilize feature re-presentations of instances in the source and target domains to eliminate domain shifts. It is worth noting that the instance features are closely related to the entire distribution of the ...

Uncoupled regression is the problem of learning a regression model from uncoupled data that consists of a set of input values (unlabeled data) and a set of output values where the correspondence between the input and output is unknown. A recent ...

Bidirectional Generative Adversarial Networks (BiGANs) is a generative model with an invertible mapping between latent and image space. The mapping allows us to encode real images into latent representations and reconstruct input images. However, ...

In this paper, we address the problem of unsupervised domain adaptation in a regression setting considering that source data have different representations (multiple views). In this work, we investigate an original method which takes advantage of ...

Neural Radiance Fields (NeRF) learn a model for the high-quality 3D-view reconstruction of a single object. Category-specific representation makes it possible to generalize to the reconstruction and even generation of multiple objects. Existing ...

Partial label learning (PLL) is a specific weakly supervised learning problem, where each training example is associated with a set of candidate labels while only one of them is the ground truth. Recently, a disambiguation-free partial label ...

We introduce the Hamiltonian Monte Carlo Particle Swarm Optimizer (HMC-PSO), an optimization algorithm that reaps the benefits of both Exponentially Averaged Momentum PSO and HMC sampling. The coupling of the position and velocity of each particle ...

Knowledge tracing (KT) is a fundamental task of intelligent education, which traces students’ knowledge states by their historical interactions. In KT, students, questions, concepts, and answers are four main types of entities, and they contain ...

The classical support vector machine is an effective classification technique. It solves a convex optimization problem to give a global solution. But it suffers from noise and outliers. To deal with this, an intuitionistic fuzzy number (IFN) is ...

Auto-encoder is a special type of artificial neural network (ANN) that is used to learn informative features from data. In the literature, the generalization performance of several machine learning models have been improved either using auto-...${}_{\mathrm{}}$

Generative Adversarial Networks (GANs) are powerful models able to synthesize data samples closely resembling the distribution of real data, yet the diversity of those generated samples is limited due to the so-called mode collapse phenomenon ...

Flocking is a very challenging problem in a multi-agent system; traditional flocking methods also require complete knowledge of the environment and a precise model for control. In this paper, we propose Evolutionary Multi-Agent Reinforcement ...

We consider the problem of estimating directed acyclic graphs from observational data. Many studies on functional causal models assume the independence of noise terms. Thus, they suffer from the typical violation of model assumption: ...

Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this ...

Convolutional Neural Networks such as U-Net are recently getting popular among researchers in many applications, such as Biomedical Image Segmentation. U-Net is one of the popular deep Convolutional Neural Networks which first contracts the input ...

This paper studies simple three-layer digital dynamical systems related to recurrent-type neural networks. The input to hidden layers construct an elementary cellular automaton and the hidden to output layers are one-to-one connection described by ...