Adversarial training is a useful approach to promote the learning of transferable representations across the source and target domains, which has been widely applied for domain adaptation (DA) tasks based on deep neural networks. Until very recently, existing adversarial domain adaptation (ADA) methods ignore the useful information from the label space, which is an important factor accountable for the complicated data distributions associated with different semantic classes. Especially, the inter-class semantic relationships have been rarely considered and discussed in the current work of transfer learning. In this paper, we propose a novel relationship-aware adversarial domain adaptation (RADA) algorithm, which first utilizes a single multi-class domain discriminator to enforce the learning of inter-class dependency structure during domain-adversarial training and then aligns this structure with the inter-class dependencies that are characterized from training the label predictor on the source domain. Specifically, we impose a regularization term to penalize the structure discrepancy between the inter-class dependencies respectively estimated from domain discriminator and label predictor. Through this alignment, our proposed method makes the ADA aware of class relationships. Empirical studies show that the incorporation of class relationships significantly improves the performance on benchmark datasets.

Estimating the uncertainty of a Bayesian model has been investigated for decades. The model posterior is almost always intractable, such that approximation is necessary. In many real-world cases, even though a decent estimation of the model posterior is obtained, another approximation is required to compute the predictive distribution over the desired output. A common accurate solution is to use Monte Carlo (MC) integration. However, it needs to maintain a large number of samples, evaluate the model repeatedly and average multiple model outputs. In this paper, we propose a method to approximate the probability distribution over the simplex induced by model posterior, enabling tractable computation of the predictive distribution for classification. The aim is to approximate the induced uncertainty of a specific Bayesian model, meanwhile alleviating the heavy workload of MC integration in testing time. Methodologically, we adapt Wasserstein distance to learn the induced conditional distributions, which is novel for Bayesian learning. The proposed method is universally applicable to Bayesian classification models that allow for posterior sampling. Empirical results validate the strong practical performance of our approach.

Many real-world open-domain conversation applications have specific goals to achieve during open-ended chats, such as recommendation, psychotherapy, education, etc. We study the problem of imposing conversational goals on open-domain chat agents. In particular, we want a conversational system to chat naturally with human and proactively guide the conversation to a designated target subject. The problem is challenging as no public data is available for learning such a target-guided strategy. We propose a structured approach that introduces coarse-grained keywords to control the intended content of system responses. We then attain smooth conversation transition through turn-level supervised learning, and drive the conversation towards the target with discourse-level constraints. We further derive a keyword-augmented conversation dataset for the study. Quantitative and human evaluations show our system can produce meaningful and effective conversations, significantly improving over other approaches.

Producing probabilistic forecasts for large collections of similar and/or dependent time series is a practically relevant and challenging task. Classical time series models fail to capture complex patterns in the data, and multivariate techniques struggle to scale to large problem sizes. Their reliance on strong structural assumptions makes them data-efficient, and allows them to provide uncertainty estimates. The converse is true for models based on deep neural networks, which can learn complex patterns and dependencies given enough data. In this paper, we propose a hybrid model that incorporates the benefits of both approaches. Our new method is data-driven and scalable via a latent, global, deep component. It also handles uncertainty through a local classical model. We provide both theoretical and empirical evidence for the soundness of our approach through a necessary and sufficient decomposition of exchangeable time series into a global and a local part. Our experiments demonstrate the advantages of our model both in term of data efficiency, accuracy and computational complexity.

Generalization is vital important for many deep network models. It becomes more challenging when high robustness is required for learning with noisy labels. The 0-1 loss has monotonic relationship between empirical adversary (reweighted) risk [8], and it is robust to outliers. However, it is also difficult to optimize. To efficiently optimize 0-1 loss while keeping its robust properties, we propose a very simple and efficient loss, i.e. curriculum loss (CL). Our CL is a tighter upper bound of the 0-1 loss compared with conventional summation based surrogate losses. Moreover, CL can adaptively select samples for training as a curriculum learning. To handle large rate of noisy label corruption, we extend our curriculum loss to a more general form that can automatically prune the estimated noisy samples during training. Experimental results on noisy MNIST, CIFAR10 and CIFAR100 dataset validate the robustness of the proposed loss.

We give a formal and complete characterization of the explicit regularizer induced by dropout in deep linear networks with squared loss. We show that (a) the explicit regularizer is composed of an $\ell_2$-path regularizer and other terms that are also re-scaling invariant, (b) the convex envelope of the induced regularizer is the squared nuclear norm of the network map, and (c) for a sufficiently large dropout rate, we characterize the global optima of the dropout objective. We validate our theoretical findings with empirical results.

Hashing has been widely adopted for large-scale data retrieval in many domains, due to its low storage cost and high retrieval speed. Existing cross-modal hashing methods optimistically assume that the correspondence between training samples across modalities are readily available. This assumption is unrealistic in practical applications. In addition, these methods generally require the same number of samples across different modalities, which restricts their flexibility. We propose a flexible cross-modal hashing approach (Flex-CMH) to learn effective hashing codes from weakly-paired data, whose correspondence across modalities are partially (or even totally) unknown. FlexCMH first introduces a clustering-based matching strategy to explore the local structure of each cluster, and thus to find the potential correspondence between clusters (and samples therein) across modalities. To reduce the impact of an incomplete correspondence, it jointly optimizes in a unified objective function the potential correspondence, the cross-modal hashing functions derived from the correspondence, and a hashing quantitative loss. An alternative optimization technique is also proposed to coordinate the correspondence and hash functions, and to reinforce the reciprocal effects of the two objectives. Experiments on publicly multi-modal datasets show that FlexCMH achieves significantly better results than state-of-the-art methods, and it indeed offers a high degree of flexibility for practical cross-modal hashing tasks.

This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a differentiable robot algorithm and an associated model; and it is trained end-to-end from data. DAN combines the strengths of model-driven modular system design and data-driven end-to-end learning. The algorithms and models act as structural assumptions to reduce the data requirements for learning; end-to-end learning allows the modules to adapt to one another and compensate for imperfect models and algorithms, in order to achieve the best overall system performance. We illustrate the DAN methodology through a case study on a simulated robot system, which learns to navigate in complex 3-D environments with only local visual observations and an image of a partially correct 2-D floor map.

Principal Component Analysis (PCA) has been used to study the pathogenesis of diseases. To enhance the interpretability of classical PCA, various improved PCA methods have been proposed to date. Among these, a typical method is the so-called sparse PCA, which focuses on seeking sparse loadings. However, the performance of these methods is still far from satisfactory due to their limitation of using unsupervised learning methods; moreover, the class ambiguity within the sample is high. To overcome this problem, this study developed a new PCA method, which is named the Supervised Discriminative Sparse PCA (SDSPCA). The main innovation of this method is the incorporation of discriminative information and sparsity into the PCA model. Specifically, in contrast to the traditional sparse PCA, which imposes sparsity on the loadings, here, sparse components are obtained to represent the data. Furthermore, via linear transformation, the sparse components approximate the given label information. On the one hand, sparse components improve interpretability over traditional PCA, while on the other hand, they are have discriminative abilities suitable for classification purposes. A simple algorithm is developed and its convergence proof is provided. The SDSPCA has been applied to common characteristic gene selection (com-characteristic gene) and tumor classification on multi-view biological data. The sparsity and classification performance of the SDSPCA are empirically verified via abundant, reasonable, and effective experiments, and the obtained results demonstrate that SDSPCA outperforms other state-of-the-art methods.

Extreme classification seeks to assign each data point, the most relevant labels from a universe of a million or more labels. This task is faced with the dual challenge of high precision and scalability, with millisecond level prediction times being a benchmark. We propose DEFRAG, an adaptive feature agglomeration technique to accelerate extreme classification algorithms. Despite past works on feature clustering and selection, DEFRAG distinguishes itself in being able to scale to millions of features, and is especially beneficial when feature sets are sparse, which is typical of recommendation and multi-label datasets. The method comes with provable performance guarantees and performs efficient task-driven agglomeration to reduce feature dimensionalities by an order of magnitude or more. Experiments show that DEFRAG can not only reduce training and prediction times of several leading extreme classification algorithms by as much as 40%, but also be used for feature reconstruction to address the problem of missing features, as well as offer superior coverage on rare labels.