--In this paper, we give an overview of the semantic gap problem in multimedia and discuss how machine learning and symbolic AI can be combined to narrow this gap. We describe the gap in terms of a classical architecture for multimedia processing and discuss a structured approach to bridge it. This approach combines machine learning (for mapping signals to objects) and symbolic AI (for linking objects to meanings). Our main goal is to raise awareness and discuss the challenges involved in this structured approach to multimedia understanding, especially in the view of the latest developments in machine learning and symbolic AI. A classic problem in multimedia representation and understanding is the semantic gap problem [1].

Knowledge graphs (KGs) serve as useful resources for various natural language processing applications. Previous KG completion approaches require a large number of training instances (i.e., head-tail entity pairs) for every relation. The real case is that for most of the relations, very few entity pairs are available. Existing work of one-shot learning limits method generalizability for few-shot scenarios and does not fully use the supervisory information; however, few-shot KG completion has not been well studied yet. In this work, we propose a novel few-shot relation learning model (FSRL) that aims at discovering facts of new relations with few-shot references. FSRL can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few-shot references, and match similar entity pairs of reference set for every relation. Extensive experiments on two public datasets demonstrate that FSRL outperforms the state-of-the-art. Introduction Large-scale knowledge graphs (KGs) such as Y AGO (Suchanek, Kasneci, and Weikum 2007), NELL (Carlson et al. 2010), and Wikidata (Vrande ˇ ci c and Kr otzsch 2014) usually represent facts in the form of relations (edges) between (head-tail) entity pairs (nodes). This kind of graph-structured knowledge is essential for many downstream applications such as search, question answering, and semantic web.

We explore adversarial robustness in the setting in which it is acceptable for a classifier to abstain---that is, output no class---on adversarial examples. Adversarial examples are small perturbations of normal inputs to a classifier that cause the classifier to give incorrect output; they present security and safety challenges for machine learning systems. In many safety-critical applications, it is less costly for a classifier to abstain on adversarial examples than to give incorrect output for them. We first introduce a novel objective function for adversarial robustness with an abstain option which characterizes an explicit tradeoff between robustness and accuracy. We then present a simple baseline in which an adversarially-trained classifier abstains on all inputs within a certain distance of the decision boundary, which we theoretically and experimentally evaluate. Finally, we propose Combined Abstention Robustness Learning (CARL), a method for jointly learning a classifier and the region of the input space on which it should abstain. We explore different variations of the PGD and DeepFool adversarial attacks on CARL in the abstain setting. Evaluating against these attacks, we demonstrate that training with CARL results in a more accurate, robust, and efficient classifier than the baseline.

The AlphaZero algorithm has achieved superhuman performance in two-player, deterministic, zero-sum games where perfect information of the game state is available. This success has been demonstrated in Chess, Shogi, and Go where learning occurs solely through self-play. Many real-world applications (e.g., equity trading) require the consideration of a multiplayer environment. In this work, we suggest novel modifications of the AlphaZero algorithm to support multiplayer environments, and evaluate the approach in two simple 3-player games. Our experiments show that multiplayer AlphaZero learns successfully and consistently outperforms a competing approach: Monte Carlo tree search. These results suggest that our modified AlphaZero can learn effective strategies in multiplayer game scenarios. Our work supports the use of AlphaZero in multiplayer games and suggests future research for more complex environments.

Graph kernels are widely used for measuring the similarity between graphs. Many existing graph kernels, which focus on local patterns within graphs rather than their global properties, suffer from significant structure information loss when representing graphs. Some recent global graph kernels, which utilizes the alignment of geometric node embeddings of graphs, yield state-of-the-art performance. However, these graph kernels are not necessarily positive-definite. More importantly, computing the graph kernel matrix will have at least quadratic {time} complexity in terms of the number and the size of the graphs. In this paper, we propose a new family of global alignment graph kernels, which take into account the global properties of graphs by using geometric node embeddings and an associated node transportation based on earth mover's distance. Compared to existing global kernels, the proposed kernel is positive-definite. Our graph kernel is obtained by defining a distribution over \emph{random graphs}, which can naturally yield random feature approximations. The random feature approximations lead to our graph embeddings, which is named as "random graph embeddings" (RGE). In particular, RGE is shown to achieve \emph{(quasi-)linear scalability} with respect to the number and the size of the graphs. The experimental results on nine benchmark datasets demonstrate that RGE outperforms or matches twelve state-of-the-art graph classification algorithms.

In this paper a new formulation of event recognition task is examined: it is required to predict event categories in a gallery of images, for which albums (groups of photos corresponding to a single event) are unknown. We propose the novel two-stage approach. At first, features are extracted in each photo using the pre-trained convolutional neural network. These features are classified individually. The scores of the classifier are used to group sequential photos into several clusters. Finally, the features of photos in each group are aggregated into a single descriptor using neural attention mechanism. This algorithm is optionally extended to improve the accuracy for classification of each image in an album. In contrast to conventional fine-tuning of convolutional neural networks (CNN) we proposed to use image captioning, i.e., generative model that converts images to textual descriptions. They are one-hot encoded and summarized into sparse feature vector suitable for learning of arbitrary classifier. Experimental study with Photo Event Collection and Multi-Label Curation of Flickr Events Dataset demonstrates that our approach is 9-20% more accurate than event recognition on single photos. Moreover, proposed method has 13-16% lower error rate than classification of groups of photos obtained with hierarchical clustering. It is experimentally shown that the image captions trained on Conceptual Captions dataset can be classified more accurately than the features from object detector, though they both are obviously not as rich as the CNN-based features. However, it is possible to combine our approach with conventional CNNs in an ensemble to provide the state-of-the-art results for several event datasets.

Hydroxyurea (HU) has been shown to be effective in alleviating the symptoms of Sickle Cell Anemia disease. While Hydroxyurea reduces the complications associated with Sickle Cell Anemia in some patients, others do not benefit from this drug and experience deleterious effects since it is also a chemotherapeutic agent. Therefore, to whom, should the administration of HU be considered as a viable option, is the main question asked by the responsible physician. We address this question by developing modeling techniques that can predict a patient's response to HU and therefore spare the non-responsive patients from the unnecessary effects of HU on the values of 22 parameters that can be obtained from blood samples in 122 patients. Using this data, we developed Deep Artificial Neural Network models that can predict with 92.6% accuracy, the final HbF value of a subject after undergoing HU therapy. Our current studies are focussing on forecasting a patient's HbF response, 30 days ahead of time.

One of the major shortcomings of variational autoencoders is the inability to produce generations from the individual modalities of data originating from mixture distributions. This is primarily due to the use of a simple isotropic Gaussian as the prior for the latent code in the ancestral sampling procedure for the data generations. We propose a novel formulation of variational autoencoders, conditional prior VAE (CP-VAE), which learns to differentiate between the individual mixture components and therefore allows for generations from the distributional data clusters. We assume a two-level generative process with a continuous (Gaussian) latent variable sampled conditionally on a discrete (categorical) latent component. The new variational objective naturally couples the learning of the posterior and prior conditionals, and the learning of the latent categories encoding the multimodality of the original data in an unsupervised manner. The data-dependent conditional priors are then used to sample the continuous latent code when generating new samples from the individual mixture components corresponding to the multimodal structure of the original data. Our experimental results illustrate the generative performance of our new model comparing to multiple baselines.

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we show that estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing them makes it possible to impose much stronger constraints encoding the conservation of the number of people, which significantly boost performance without requiring a more complex architecture. Furthermore, it also enables us to exploit the correlation between people flow and optical flow to further improve the results. We will demonstrate that we consistently outperform state-of-the-art methods on five benchmark datasets.

The phenomenon of ellipsis is prevalent in social conversations. Ellipsis increases the difficulty of a series of downstream language understanding tasks, such as dialog act prediction and semantic role labeling. We propose to resolve ellipsis through automatic sentence completion to improve language understanding. However, automatic ellipsis completion can result in output which does not accurately reflect user intent. To address this issue, we propose a method which considers both the original utterance that has ellipsis and the automatically completed utterance in dialog act and semantic role labeling tasks. Specifically, we first complete user utterances to resolve ellipsis using an end-to-end pointer network model. We then train a prediction model using both utterances containing ellipsis and our automatically completed utterances. Finally, we combine the prediction results from these two utterances using a selection model that is guided by expert knowledge. Our approach improves dialog act prediction and semantic role labeling by 1.3% and 2.5% in F1 score respectively in social conversations. We also present an open-domain human-machine conversation dataset with manually completed user utterances and annotated semantic role labeling after manual completion. Introduction Ellipsis, in which a speaker omits words that are understood from context, is a frequent phenomenon in human conversation. Although natural to humans, ellipsis poses a challenge for language understanding in spoken dialog systems.