We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied on many image pixel-wise prediction tasks, similar methods are lacking for graph data. This is due to the fact that pooling and up-sampling operations are not natural on graph data. To address these challenges, we propose novel graph pooling (gPool) and unpooling (gUnpool) operations in this work. The gPool layer adaptively selects some nodes to form a smaller graph based on their scalar projection values on a trainable projection vector. We further propose the gUnpool layer as the inverse operation of the gPool layer. The gUnpool layer restores the graph into its original structure using the position information of nodes selected in the corresponding gPool layer. Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models.

Distance metric learning is successful in discovering intrinsic relations in data. However, most algorithms are computationally demanding when the problem size becomes large. In this paper, we propose a discriminative metric learning algorithm, and develop a distributed scheme learning metrics on moderate-sized subsets of data, and aggregating the results into a global solution. The technique leverages the power of parallel computation. The algorithm of the aggregated distance metric learning (ADML) scales well with the data size and can be controlled by the partition. We theoretically analyse and provide bounds for the error induced by the distributed treatment. We have conducted experimental evaluation of ADML, both on specially designed tests and on practical image annotation tasks. Those tests have shown that ADML achieves the state-of-the-art performance at only a fraction of the cost incurred by most existing methods.

We consider a distributed system of $m$ machines and a server. Each machine draws $n$ i.i.d samples from an unknown distribution and sends a message of bounded length $b$ to the server. The server then collects messages from all machines and estimates a parameter that minimizes an expected loss. We investigate the impact of communication constraint, $b$, on the expected error; and derive lower bounds on the best error achievable by any algorithm. As our main result, for general values of $b$, we establish a $\tilde{\Omega}\big( (mb)^{-{1}/{\max(d,2)}} n^{-1/2} \big)$ lower bounded on the expected error, where $d$ is the dimension of the parameter space. Moreover, for constant values of $b$ and under the extra assumption $n=1$, we show that expected error remains lower bounded by a constant, even when $m$ tends to infinity.

Robustness recently becomes one of the major concerns among machine learning community, since learning algorithms are usually vulnerable to outliers or corruptions. Motivated by such a trend and needs, we pursue robustness in semi-definite programming (SDP) in this paper. Specifically, this is done by replacing the commonly used squared loss with the more robust $\ell_1$-loss in the low-rank SDP. However, the resulting objective becomes neither convex nor smooth. As no existing algorithms can be applied, we design an efficient algorithm, based on majorization-minimization, to optimize the objective. The proposed algorithm not only has cheap iterations and low space complexity but also theoretically converges to some critical points. Finally, empirical study shows that the new objective armed with proposed algorithm outperforms state-of-the-art in terms of both speed and accuracy.

Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet comparatively little attention has been paid to explaining their predictions. Here we significantly improve the interpretability of tree-based models through three main contributions: 1) The first polynomial time algorithm to compute optimal explanations based on game theory. 2) A new type of explanation that directly measures local feature interaction effects. 3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction. We apply these tools to three medical machine learning problems and show how combining many high-quality local explanations allows us to represent global structure while retaining local faithfulness to the original model. These tools enable us to i) identify high magnitude but low frequency non-linear mortality risk factors in the general US population, ii) highlight distinct population sub-groups with shared risk characteristics, iii) identify non-linear interaction effects among risk factors for chronic kidney disease, and iv) monitor a machine learning model deployed in a hospital by identifying which features are degrading the model's performance over time. Given the popularity of tree-based machine learning models, these improvements to their interpretability have implications across a broad set of domains.

Deep generative models are effective methods of modeling data. However, it is not easy for a single generative model to faithfully capture the distributions of complex data such as images. In this paper, we propose an approach for boosting generative models, which cascades meta-models together to produce a stronger model. Any hidden variable meta-model (e.g., RBM and VAE) which supports likelihood evaluation can be leveraged. We derive a decomposable variational lower bound of the boosted model, which allows each meta-model to be trained separately and greedily. Besides, our framework can be extended to semi-supervised boosting, where the boosted model learns a joint distribution of data and labels. Finally, we combine our boosting framework with the multiplicative boosting framework, which further improves the learning power of generative models.

Cross-modal hashing has been receiving increasing interests for its low storage cost and fast query speed in multi-modal data retrievals. However, most existing hashing methods are based on hand-crafted or raw level features of objects, which may not be optimally compatible with the coding process. Besides, these hashing methods are mainly designed to handle simple pairwise similarity. The complex multilevel ranking semantic structure of instances associated with multiple labels has not been well explored yet. In this paper, we propose a ranking-based deep cross-modal hashing approach (RDCMH). RDCMH firstly uses the feature and label information of data to derive a semi-supervised semantic ranking list. Next, to expand the semantic representation power of hand-crafted features, RDCMH integrates the semantic ranking information into deep cross-modal hashing and jointly optimizes the compatible parameters of deep feature representations and of hashing functions. Experiments on real multi-modal datasets show that RDCMH outperforms other competitive baselines and achieves the state-of-the-art performance in cross-modal retrieval applications.

As many as one billion people--15 per cent of the world's population--have some form of disability, with around three per cent suffering from severe disabilities, according to World Bank. For most of these people, accessing modern technology and all it has to offer presents a host of difficulties. Even something as simple as using a cell phone can be impossible. Global Accessibility Awareness Day (May 16) aims to combat that. Launched in 2015, the day is designed to get everyone thinking and talking about improving digital access and inclusion for people with disabilities.

A boat carrying a cargo of British oysters across the English Channel has become the world's first ever shipment completed using remote control. Mersea Island molluscs were on-board the 40-foot (12 m) long Sea-Kit vessel heading to Orstend in Belgium and there was not a single human being on-board. It successfully completed the delivery of the 11 pounds (5kg) of shellfish and then made a return journey with some Belgian beer on-board. Myriad technological gadgets and innovations fed data back to a control room in Maldon, Essex where two workers completed the 22-hour trip. The British vessel is equipped with cameras, radar, microphones, thermal imaging and a back-up autonomous system to keep it and other sea-goers safe.

Voice recordings captured by Amazon's Alexa can be deleted but the automatically produced transcriptions remain in the company's cloud, according to reports. After Alexa hears its'wake' word, the smart assistant starts listening and transcribing everything it hears. All the voice commands said to the virtual assistant can be deleted from the central system, but the company still has the the text logs, according to CNET. This data is kept on its cloud servers, with no option for users to delete it, but the company claims it is working on ways to make the data inaccessible. Amazon workers are listening to private and sometimes disturbing voice recordings to improve the voice-assistants understanding of human speech.