Curriculum Learning (CL) mimics the cognitive process ofhumans and favors a learning algorithm to follow the logical learning sequence from simple examples to more difficult ones. Recent studies show that selecting the simplest curriculum examples from different modalities for graph-based label propagation can yield better performance than simply leveraging single modality. However, they forcibly requirethe curriculums generated by all modalities to be identical to a common curriculum, which discard the individuality ofevery modality and produce the inaccurate curriculum for the subsequent learning. Therefore, this paper proposes a novel multi-modal CL algorithm by comprehensively investigating both the individuality and commonality of different modalities. By considering the curriculums of multiple modalities altogether, their common preference on selecting the simplestexamples can be explored by a row-sparse matrix, and their distinct opinions are captured by a sparse noise matrix. As a consequence, a "soft" fusion of multiple curriculums from different modalities is achieved and the propagation quality can thus be improved. Comprehensive empirical studies reveal that our method can generate higher accuracy than the state-of-the-art multi-modal CL approach and label propagation algorithms on various image classification tasks.

In many real world applications, the concerned objects are with multiple labels, and can be represented as a bag of instances. Multi-instance Multi-label (MIML) learning provides a framework for handling such task and has exhibited excellent performance in various domains. In a MIML setting, the feature representation of instances usually has big impact on the final performance; inspired by the recent deep learning studies, in this paper, we propose the DeepMIML network which exploits deep neural network formation to generate instance representation for MIML. The sub-concept learning component of the DeepMIML structure reserves the instance-label relation discovery ability of MIML algorithms; that is, it can automatically locating the key input patterns that trigger the labels. The effectiveness of DeepMIML network is validated by experiments on various domains of data.

Recently, there has been an increasing interest in designing distributed convex optimization algorithms under the setting where the data matrix is partitioned on features. Algorithms under this setting sometimes have many advantages over those under the setting where data is partitioned on samples, especially when the number of features is huge. Therefore, it is important to understand the inherent limitations of these optimization problems. In this paper, with certain restrictions on the communication allowed in the procedures, we develop tight lower bounds on communication rounds for a broad class of non-incremental algorithms under this setting. We also provide a lower bound on communication rounds for a class of (randomized) incremental algorithms.

We are interested in exploring the possibility and benefits of structure learning for deep models. As the first step, this paper investigates the matter for Restricted Boltzmann Machines (RBMs) . We conduct the study with Replicated Softmax, a variant of RBMs for unsupervised text analysis. We present a method for learning what we call Sparse Boltzmann Machines , where each hidden unit is connected to a subset of the visible units instead of all of them.  Empirical results show that the method yields models with significantly improved model fit and interpretability as compared with RBMs where each hidden unit is connected to all visible units.

We present a new perspective on the popular multi-class algorithmic techniques of one-vs-all and error correcting output codes. Rather than studying the behavior of these techniques for supervised learning, we establish a connection between the success of these methods and the existence of label-efficient learning procedures. We show that in both the realizable and agnostic cases, if output codes are successful at learning from labeled data, they implicitly assume structure on how the classes are related. By making that structure explicit, we design learning algorithms to recover the classes with low label complexity. We provide results for the commonly studied cases of one-vs-all learning and when the codewords of the classes are well separated. We additionally consider the more challenging case where the codewords are not well separated, but satisfy a boundary features condition that captures the natural intuition that every bit of the codewords should be significant.

We present new algorithms for learning Bayesian networks from data with missing values using a data augmentation approach. An exact Bayesian network learning algorithm is obtained by recasting the problem into a standard Bayesian network learning problem without missing data. As expected, the exact algorithm does not scale to large domains. We build on the exact method to create an approximate algorithm using a hill-climbing technique. This algorithm scales to large domains so long as a suitable standard structure learning method for complete data is available. We perform a wide range of experiments to demonstrate the benefits of learning Bayesian networks with such new approach.

Forecasting the flow of crowds is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, such as inter-region traffic, events, and weather. We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast the inflow and outflow of crowds in each and every region of a city. We design an end-to-end structure of ST-ResNet based on unique properties of spatio-temporal data. More specifically, we employ the residual neural network framework to model the temporal closeness, period, and trend properties of crowd traffic. For each property, we design a branch of residual convolutional units, each of which models the spatial properties of crowd traffic. ST-ResNet learns to dynamically aggregate the output of the three residual neural networks based on data, assigning different weights to different branches and regions. The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region. Experiments on two types of crowd flows in Beijing and New York City (NYC) demonstrate that the proposed ST-ResNet outperforms six well-known methods.

Boundary incompleteness raises great challenges to automatic prostate segmentation in ultrasound images. Shape prior can provide strong guidance in estimating the missing boundary, but traditional shape models often suffer from hand-crafted descriptors and local information loss in the fitting procedure. In this paper, we attempt to address those issues with a novel framework. The proposed framework can seamlessly integrate feature extraction and shape prior exploring, and estimate the complete boundary with a sequential manner. Our framework is composed of three key modules. Firstly, we serialize the static 2D prostate ultrasound images into dynamic sequences and then predict prostate shapes by sequentially exploring shape priors. Intuitively, we propose to learn the shape prior with the biologically plausible Recurrent Neural Networks (RNNs). This module is corroborated to be effective in dealing with the boundary incompleteness. Secondly, to alleviate the bias caused by different serialization manners, we propose a multi-view fusion strategy to merge shape predictions obtained from different perspectives. Thirdly, we further implant the RNN core into a multiscale Auto-Context scheme to successively refine the details of the shape prediction map. With extensive validation on challenging prostate ultrasound images, our framework bridges severe boundary incompleteness and achieves the best performance in prostate boundary delineation when compared with several advanced methods. Additionally, our approach is general and can be extended to other medical image segmentation tasks, where boundary incompleteness is one of the main challenges.

Dictionary learning has played an important role in the success of sparse representation, which triggers the rapid developments of unsupervised and supervised dictionary learning methods. However, in most practical applications, there are usually quite limited labeled training samples while it is relatively easy to acquire abundant unlabeled training samples. Thus semi-supervised dictionary learning that aims to effectively explore the discrimination of unlabeled training data has attracted much attention of researchers. Although various regularizations have been introduced in the prevailing semi-supervised dictionary learning, how to design an effective unified model of dictionary learning and unlabeled-data class estimating and how to well explore the discrimination in the labeled and unlabeled data are still open. In this paper, we propose a novel discriminative semi-supervised dictionary learning model (DSSDL) by introducing discriminative representation, an identical coding of unlabeled data to the coding of testing data final classification, and an entropy regularization term. The coding strategy of unlabeled data can not only avoid the affect of its incorrect class estimation, but also make the learned discrimination be well exploited in the final classification. The introduced regularization of entropy can avoid overemphasizing on some uncertain estimated classes for unlabeled samples. Apart from the enhanced discrimination in the learned dictionary by the discriminative representation, an extended dictionary is used to mainly explore the discrimination embedded in the unlabeled data. Extensive experiments on face recognition, digit recognition and texture classification show the effectiveness of the proposed method.

With benefits of low storage cost and fast query speed, cross-modal hashing has received considerable attention recently. However, almost all existing methods on cross-modal hashing cannot obtain powerful hash codes due to directly utilizing hand-crafted features or ignoring heterogeneous correlations across different modalities, which will greatly degrade the retrieval performance. In this paper, we propose a novel deep cross-modal hashing method to generate compact hash codes through an end-to-end deep learning architecture, which can effectively capture the intrinsic relationships between various modalities. Our architecture integrates different types of pairwise constraints to encourage the similarities of the hash codes from an intra-modal view and an inter-modal view, respectively. Moreover, additional decorrelation constraints are introduced to this architecture, thus enhancing the discriminative ability of each hash bit. Extensive experiments show that our proposed method yields state-of-the-art results on two cross-modal retrieval datasets.