Neural architecture search-based multi-modal classification (NAS-MMC) methods can individually obtain the optimal classifier for different multi-modal data sets in an automatic manner. However, most existing NAS-MMC methods are dramatically time consuming due to the requirement for training and evaluating enormous models. In this paper, we propose an efficient evolutionary-based NAS-MMC method called divide-and-conquer neural architecture search (DC-NAS). Specifically, the evolved population is first divided into k+1 sub-populations, and then k sub-populations of them evolve on k small-scale data sets respectively that are obtained by splitting the entire data set using the k-fold stratified sampling technique; the remaining one evolves on the entire data set. To solve the sub-optimal fusion model problem caused by the training strategy of partial data, two kinds of sub-populations that are trained using partial data and entire data exchange the learned knowledge via two special knowledge bases. With the two techniques mentioned above, DC-NAS achieves the training time reduction and classification performance improvement. Experimental results show that DC-NAS achieves the state-of-the-art results in term of classification performance, training efficiency and the number of model parameters than the compared NAS-MMC methods on three popular multi-modal tasks including multi-label movie genre classification, action recognition with RGB and body joints and dynamic hand gesture recognition.

Multi-task learning deals with multiple related tasks simultaneously by sharing knowledge. In a typical deep multi-task learning model, all tasks use the same feature space and share the latent knowledge. If the tasks are weakly correlated or some features are negatively correlated, sharing all knowledge often leads to negative knowledge transfer among. To overcome this issue, this paper proposes a Fisher sparse multi-task learning method. It can obtain a sparse sharing representation for each task. In such a way, tasks share features on a sparse subspace. Our method can ensure that the knowledge transferred among tasks is beneficial. Specifically, we first propose a sparse deep multi-task learning model, and then introduce Fisher sparse module into traditional deep multi-task learning to learn the sparse variables of task. By alternately updating the neural network parameters and sparse variables, a sparse sharing representation can be learned for each task. In addition, in order to reduce the computational overhead, an heuristic method is used to estimate the Fisher information of neural network parameters. Experimental results show that, comparing with other methods, our proposed method can improve the performance for all tasks, and has high sparsity in multi-task learning.

Most current data is multivariable, exploring and identifying valuable information in these datasets has far-reaching impacts. In particular, discovering meaningful hidden association patterns in multivariate plays an important role. Plenty of measures for multivariate association have been proposed, yet it is still an open research challenge for effectively capturing association patterns among three or more variables, especially the scenario without any prior knowledge about those relationships. To do so, we desire a distribution-free, association type-independent and non-parametrical measure. For practical applications, such a measure should comparable, interpretable,scalable, intuitive, reliability, and robust. However, no exiting measures fulfill all of these desiderata. In this paper, taking advantage of the neighborhood information of a sample, we propose MNA, a maximal neighborhood multivariate association measure that satisfies all the above criteria. Extensive experiments on synthetic and real data show it outperforms state-of-the-art multivariate association measures.

Representation and learning of concepts are critical problems in data science and cognitive science. However, the existing research about concept learning has one prevalent disadvantage: incomplete and complex cognitive. Meanwhile, as a practical mathematical tool for concept representation and concept learning, two-way learning (2WL) also has some issues leading to the stagnation of its related research: the concept can only learn from specific information granules and lacks a concept evolution mechanism. To overcome these challenges, we propose the two-way concept-cognitive learning (TCCL) method for enhancing the flexibility and evolution ability of 2WL for concept learning. We first analyze the fundamental relationship between two-way granule concepts in the cognitive system to build a novel cognitive mechanism. Furthermore, the movement three-way decision (M-3WD) method is introduced to 2WL to study the concept evolution mechanism via the concept movement viewpoint. Unlike the existing 2WL method, the primary consideration of TCCL is two-way concept evolution rather than information granules transformation. Finally, to interpret and help understand TCCL, an example analysis and some experiments on various datasets are carried out to demonstrate our method's effectiveness. The results show that TCCL is more flexible and less time-consuming than 2WL, and meanwhile, TCCL can also learn the same concept as the latter method in concept learning. In addition, from the perspective of concept learning ability, TCCL is more generalization of concepts than the granule concept cognitive learning model (CCLM).