Deep Multi-View Concept Learning

Xu, Cai; Guan, Ziyu; Zhao, Wei; Niu, Yunfei; Wang, Quan; Wang, Zhiheng

doi:10.24963/ijcai.2018/402

Cited by 36 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, how humans require only one or a few examples to acquire a concept is incorporated through one-shot or few-shot learning or how known concepts can be used to recognize new exemplars is achieved through incremental learning and memory modules. Many more approaches to concept learning using deep learning techniques exist (e.g., Wang et al, 2015 ; Dolgikh, 2018 ; Xu et al, 2018 ; Rodriguez et al, 2019 ). In general, these approaches yield high levels of accuracy but require huge amounts of training data and/or training time.…”

Section: Related Workmentioning

confidence: 99%

From Continuous Observations to Symbolic Concepts: A Discrimination-Based Strategy for Grounded Concept Learning

2020

View full text Add to dashboard Cite

Autonomous agents perceive the world through streams of continuous sensori-motor data. Yet, in order to reason and communicate about their environment, agents need to be able to distill meaningful concepts from their raw observations. Most current approaches that bridge between the continuous and symbolic domain are using deep learning techniques. While these approaches often achieve high levels of accuracy, they rely on large amounts of training data, and the resulting models lack transparency, generality, and adaptivity. In this paper, we introduce a novel methodology for grounded concept learning. In a tutor-learner scenario, the method allows an agent to construct a conceptual system in which meaningful concepts are formed by discriminative combinations of prototypical values on human-interpretable feature channels. We evaluate our approach on the CLEVR dataset, using features that are either simulated or extracted using computer vision techniques. Through a range of experiments, we show that our method allows for incremental learning, needs few data points, and that the resulting concepts are general enough to be applied to previously unseen objects and can be combined compositionally. These properties make the approach well-suited to be used in robotic agents as the module that maps from continuous sensory input to grounded, symbolic concepts that can then be used for higher-level reasoning tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

From Continuous Observations to Symbolic Concepts: A Discrimination-Based Strategy for Grounded Concept Learning

2020

View full text Add to dashboard Cite

show abstract

“…In fact, exploring consistent or complementary information among multiple views is an important research direction [10]. Recently, [12,13] have also shown that simultaneously discerning these two kinds of information can achieve better representation learning, but they belong to semi-supervised learning-based methods, i.e., partial label information of multi-view data must be provided. Therefore, it is still worth researching how to learn a low-dimensional representation with consistent and complementary information across multiple views via neural networks for multi-view clustering.…”

Section: Introductionmentioning

confidence: 99%

Deep Multiple Auto-Encoder-Based Multi-view Clustering

Zhou

Yang

et al. 2021

Data Sci. Eng.

View full text Add to dashboard Cite

Multi-view clustering (MVC), which aims to explore the underlying structure of data by leveraging heterogeneous information of different views, has brought along a growth of attention. Multi-view clustering algorithms based on different theories have been proposed and extended in various applications. However, most existing MVC algorithms are shallow models, which learn structure information of multi-view data by mapping multi-view data to low-dimensional representation space directly, ignoring the nonlinear structure information hidden in each view, and thus, the performance of multi-view clustering is weakened to a certain extent. In this paper, we propose a deep multi-view clustering algorithm based on multiple auto-encoder, termed MVC-MAE, to cluster multi-view data. MVC-MAE adopts auto-encoder to capture the nonlinear structure information of each view in a layer-wise manner and incorporate the local invariance within each view and consistent as well as complementary information between any two views together. Besides, we integrate the representation learning and clustering into a unified framework, such that two tasks can be jointly optimized. Extensive experiments on six real-world datasets demonstrate the promising performance of our algorithm compared with 15 baseline algorithms in terms of two evaluation metrics.

show abstract

“…Inspired by the recent amazing success of deep learning in feature learning (Hinton and Salakhutdinov 2006), a surge of multi-view learning based on deep neural networks (DNN) are proposed (Ngiam et al 2011;Wang et al 2015;Xu et al 2018). First, Ngiam et al (Ngiam et al 2011) explored extracting shared representations by training a bimodal deep autoencoders.…”

Section: Introductionmentioning

confidence: 99%

“…However, unfortunately the aforementioned can only be feasible to the two-view case, failing to handle the multi-view one. To explicitly summarize the consensus and complementary information in multi-view data, a Deep Multi-view Concept learning (DMCL) (Xu et al 2018) is presented by performing non-negative factorization on every view hierarchically.…”

Section: Introductionmentioning

confidence: 99%

Shared Generative Latent Representation Learning for Multi-View Clustering

Yin

Huang

Gao

2020

AAAI

View full text Add to dashboard Cite

Clustering multi-view data has been a fundamental research topic in the computer vision community. It has been shown that a better accuracy can be achieved by integrating information of all the views than just using one view individually. However, the existing methods often struggle with the issues of dealing with the large-scale datasets and the poor performance in reconstructing samples. This paper proposes a novel multi-view clustering method by learning a shared generative latent representation that obeys a mixture of Gaussian distributions. The motivation is based on the fact that the multi-view data share a common latent embedding despite the diversity among the various views. Specifically, benefitting from the success of the deep generative learning, the proposed model can not only extract the nonlinear features from the views, but render a powerful ability in capturing the correlations among all the views. The extensive experimental results on several datasets with different scales demonstrate that the proposed method outperforms the state-of-the-art methods under a range of performance criteria.

show abstract

Deep Multi-View Concept Learning

Cited by 36 publications

References 11 publications

From Continuous Observations to Symbolic Concepts: A Discrimination-Based Strategy for Grounded Concept Learning

From Continuous Observations to Symbolic Concepts: A Discrimination-Based Strategy for Grounded Concept Learning

Deep Multiple Auto-Encoder-Based Multi-view Clustering

Shared Generative Latent Representation Learning for Multi-View Clustering

Contact Info

Product

Resources

About