Abstract--Matrix factorization (MF) has been widely used to discover the low-rank structure and to predict the missing entries of data matrix. In many real-world learning systems, the data matrix can be very high-dimensional but sparse. This poses an imbalanced learning problem, since the scale of missing entries is usually much larger than that of observed entries, but they cannot be ignored due to the valuable negative signal. For efficiency concern, existing work typically applies a uniform weight on missing entries to allow a fast learning algorithm. However, this simplification will decrease modeling fidelity, resulting in suboptimal performance for downstream applications. In this work, we weight the missing data non-uniformly, and more generically, we allow any weighting strategy on the missing data. To address the efficiency challenge, we propose a fast learning method, for which the time complexity is determined by the number of observed entries in the data matrix, rather than the matrix size. The key idea is twofold: 1) we apply truncated SVD on the weight matrix to get a more compact representation of the weights, and 2) we learn MF parameters with element-wise alternating least squares (eALS) and memorize the key intermediate variables to avoid repeating computations that are unnecessary. We conduct extensive experiments on two recommendation benchmarks, demonstrating the correctness, efficiency, and effectiveness of our fast eALS method. Atrices are a common data structure to represent the relation between two types of entities in learning systems [1]-[3]. In relational learning, matrix factorization (MF) is a popular approach for dimension reduction by representing the rows (entities of one type) and columns (entities of another type) as two low-rank matrices. The optimization of dimension reduction is usually achieved by minimizing the reconstruction error between the low-rank model and the original data. Xiangnan He and Tat-Seng Chua are with the School of Computing, National University of Singapore, Singapore, 117417. Jinhui Tang is with the School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China, 210094.

We investigate 1) the rate at which refined properties of the empirical risk---in particular, gradients---converge to their population counterparts in standard non-convex learning tasks, and 2) the consequences of this convergence for optimization. Our analysis follows the tradition of norm-based capacity control. We propose vector-valued Rademacher complexities as a simple, composable, and user-friendly tool to derive dimension-free uniform convergence bounds for gradients in non-convex learning problems. As an application of our techniques, we give a new analysis of batch gradient descent methods for non-convex generalized linear models and non-convex robust regression, showing how to use any algorithm that finds approximate stationary points to obtain optimal sample complexity, even when dimension is high or possibly infinite and multiple passes over the dataset are allowed. Moving to non-smooth models we show----in contrast to the smooth case---that even for a single ReLU it is not possible to obtain dimension-independent convergence rates for gradients in the worst case. On the positive side, it is still possible to obtain dimension-independent rates under a new type of distributional assumption.

Most of the datasets normally contain either numeric or categorical features. Mixed data comprises of both numeric and categorical features, and they frequently occur in various domains, such as health, finance, marketing, etc. Clustering is often sought on mixed data to find structures and to group similar objects. However, clustering mixed data is challenging because it is difficult to directly apply mathematical operations, such as summation, average etc. on the feature values of these datasets. In this paper, we review various types of mixed data clustering techniques in detail. We present a taxonomy to identify ten types of different mixed data clustering techniques. We also compare the performance of several mixed data clustering methods on publicly available datasets. The paper further identifies challenges in developing different mixed data clustering algorithms and provides guidelines for future directions in this area.

Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning. Prior work has developed different kinds of shaping methods that enable agents to learn efficiently in complex environments. All these methods, however, tailor human guidance to agents in specialized shaping procedures, thus embodying various characteristics and advantages in different domains. In this paper, we investigate the interplay between different shaping methods for more robust learning performance. We propose an adaptive shaping algorithm which is capable of learning the most suitable shaping method in an on-line manner. Results in two classic domains verify its effectiveness from both simulated and real human studies, shedding some light on the role and impact of human factors in human-robot collaborative learning.

We propose DecaProp (Densely Connected Attention Propagation), a new densely connected neural architecture for reading comprehension (RC). There are two distinct characteristics of our model. Firstly, our model densely connects all pairwise layers of the network, modeling relationships between passage and query across all hierarchical levels. Secondly, the dense connectors in our network are learned via attention instead of standard residual skip-connectors. To this end, we propose novel Bidirectional Attention Connectors (BAC) for efficiently forging connections throughout the network. We conduct extensive experiments on four challenging RC benchmarks. Our proposed approach achieves state-of-the-art results on all four, outperforming existing baselines by up to $2.6\%-14.2\%$ in absolute F1 score.

Some of China's smartest high school graduates have been recruited to study the manufacturing of AI weaponry to keep Beijing ahead of the war game. The Chinese teenagers are studying at Beijing Institute of Technology, a top university in the country specialising in engineering and national defence. The class, unveiled last month, comprises 31 students who are selected based on their academic achievements and their level of patriotism, according the school. AI weapons, called by some as'killer robots', generally mean automated weapons which select, engage and eliminate human targets without the involvement of other humans. It has been described as the third revolution in warfare - after gunpowder and nuclear arms - and has been a controversial topic due to the ethics behind them.

Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient. The iteration complexity for those methods therefore scales with the size of the graphical models. In this paper, we propose \emph{block belief propagation learning} (BBPL), which uses block-coordinate updates of approximate marginals to compute approximate gradients, removing the need to compute inference on the entire graphical model. Thus, the iteration complexity of BBPL does not scale with the size of the graphs. We prove that the method converges to the same solution as that obtained by using full inference per iteration, despite these approximations, and we empirically demonstrate its scalability improvements over standard training methods.

In recent years, distance education has enjoyed a major boom. Much work at The Open University (OU) has focused on improving retention rates in these modules by providing timely support to students who are at risk of failing the module. In this paper we explore methods for analysing student activity in online virtual learning environment (VLE) -- General Unary Hypotheses Automaton (GUHA) and Markov chain-based analysis -- and we explain how this analysis can be relevant for module tutors and other student support staff. We show that both methods are a valid approach to modelling student activities. An advantage of the Markov chain-based approach is in its graphical output and in the possibility to model time dependencies of the student activities.

Executing natural language navigation instructions from raw observations requires solving language, perception, planning, and control problems. Consider instructing a quadcopter drone using natural language. Figure 1 shows an example instruction. Resolving the instruction requires identifying the blue fence, anvil and tree in the world, understanding the spatial constraints towards and on the right, planning a trajectory that satisfies these constraints, and continuously controlling the quadcopter to follow the trajectory. Existing work has addressed this problem mostly using manually-designed symbolic representations for language meaning and environment [1, 2, 3, 4, 5, 6].

Achieving coordination is crucial in organizational control. This paper investigates a middle ground solution between decentralized interactions and centralized administrations for coordinating agents beyond inefficient behavior. We first propose the price of governance (PoG) to evaluate how such a middle ground solution performs in terms of effectiveness and cost. We then propose a hierarchical supervision framework to explicitly model the PoG, and define step by step how to realize the core principle of the framework and compute the optimal PoG for a control problem. Two illustrative case studies are carried out to exemplify the applications of the proposed framework and its methodology. Results show that by properly formulating and implementing each step, the hierarchical supervision framework is capable of promoting coordination among agents while bounding administrative cost to a minimum in different kinds of organizational control problems.