The newly emerged machine learning (e.g. deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial technology, and surveillance systems. Meanwhile, privacy has emerged as a big concern in this machine learning-based artificial intelligence era. It is important to note that the problem of privacy preservation in the context of machine learning is quite different from that in traditional data privacy protection, as machine learning can act as both friend and foe. Currently, the work on the preservation of privacy and machine learning (ML) is still in an infancy stage, as most existing solutions only focus on privacy problems during the machine learning process. Therefore, a comprehensive study on the privacy preservation problems and machine learning is required. This paper surveys the state of the art in privacy issues and solutions for machine learning. The survey covers three categories of interactions between privacy and machine learning: (i) private machine learning, (ii) machine learning aided privacy protection, and (iii) machine learning-based privacy attack and corresponding protection schemes. The current research progress in each category is reviewed and the key challenges are identified. Finally, based on our in-depth analysis of the area of privacy and machine learning, we point out future research directions in this field.

Federated learning (FL) has attracted increasing attention in recent years. As a privacy-preserving collaborative learning paradigm, it enables a broader range of applications, especially for computer vision and natural language processing tasks. However, to date, there is limited research of federated learning on relational data, namely Knowledge Graph (KG). In this work, we present a modified version of the graph neural network algorithm that performs federated modeling over KGs across different participants. Specifically, to tackle the inherent data heterogeneity issue and inefficiency in algorithm convergence, we propose a novel optimization algorithm, named FedAlign, with 1) optimal transportation (OT) for on-client personalization and 2) weight constraint to speed up the convergence. Extensive experiments have been conducted on several widely used datasets. Empirical results show that our proposed method outperforms the state-of-the-art FL methods, such as FedAVG and FedProx, with better convergence.

Time series are all around in real-world applications. However, unexpected accidents for example broken sensors or missing of the signals will cause missing values in time series, making the data hard to be utilized. It then does harm to the downstream applications such as traditional classification or regression, sequential data integration and forecasting tasks, thus raising the demand for data imputation. Currently, time series data imputation is a well-studied problem with different categories of methods. However, these works rarely take the temporal relations among the observations and treat the time series as normal structured data, losing the information from the time data. In recent, deep learning models have raised great attention. Time series methods based on deep learning have made progress with the usage of models like RNN, since it captures time information from data. In this paper, we mainly focus on time series imputation technique with deep learning methods, which recently made progress in this field. We will review and discuss their model architectures, their pros and cons as well as their effects to show the development of the time series imputation methods.

Graphs play an important role in many applications. Recently, Graph Neural Networks (GNNs) have achieved promising results in graph analysis tasks. Some state-of-the-art GNN models have been proposed, e.g., Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), etc. Despite these successes, most of the GNNs only have shallow structure. This causes the low expressive power of the GNNs. To fully utilize the power of the deep neural network, some deep GNNs have been proposed recently. However, the design of deep GNNs requires significant architecture engineering. In this work, we propose a method to automate the deep GNNs design. In our proposed method, we add a new type of skip connection to the GNNs search space to encourage feature reuse and alleviate the vanishing gradient problem. We also allow our evolutionary algorithm to increase the layers of GNNs during the evolution to generate deeper networks. We evaluate our method in the graph node classification task. The experiments show that the GNNs generated by our method can obtain state-of-the-art results in Cora, Citeseer, Pubmed and PPI datasets.

The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments according to the given language instruction. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments; second, during the training process, the agent usually imitate the shortest-path to the target location. Due to the discrepancy of action selection between training and inference, the agent solely on the basis of imitation learning does not perform well. Sampling the next action from its predicted probability distribution during the training process allows the agent to explore diverse routes from the environments, yielding higher success rates. Nevertheless, without being presented with the shortest navigation paths during the training process, the agent may arrive at the target location through an unexpected longer route. To overcome these challenges, we design a cross-modal grounding module, which is composed of two complementary attention mechanisms, to equip the agent with a better ability to track the correspondence between the textual and visual modalities. We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference. We further exploit the advantages of both these two learning schemes via adversarial learning. Extensive experimental results on the Room-to-Room (R2R) benchmark dataset demonstrate that the proposed learning scheme is generalized and complementary to prior arts. Our method performs well against state-of-the-art approaches in terms of effectiveness and efficiency.

Earlier this month, YouTube said it would remove videos containing misinformation about COVID-19 vaccines and would expand its current rules against falsehoods and conspiracy theories about the Pandemic. It also revealed it's removed over 200,000 videos containing dangerous or misleading COVID-19 information since early February. No wonder the World Health Organisation says the world isn't just fighting a pandemic, but an'infodemic' as well. As The New York Times recently put it, we are facing "the mass distortion of truth and overwhelming waves of speech from extremists that smear and distract". The problem, allege citizen data scientists: the infodemic isn't just crazy people talking to each other online, which in 2020 is basically BAU.

Artificial intelligence (AI) is steadily becoming a familiar tool for many Australians. We have come to know it through our pocket voice assistants, like Siri and Alexa, and as the brains behind Google's predictive searches. Australian businesses, particularly in the mining sector, view it as a means to gain a competitive advantage, and we have even seen its potential to fight COVID-19. As AI begins to permeate every aspect of our lives, the Australian government has recognised the economic and social opportunities it affords us in its newly proposed AI Action Plan. The discussion paper, released on 29 October 2020, is the latest in a suite of Australian initiatives targeting AI regulation and development, following on from the AI Ethics Framework.

To help its service technicians more efficiently repair and maintain its models, Mercedes-Benz USA is outfitting all of its authorized American dealerships with HoloLens 2 headsets. The devices are equipped with Microsoft Dynamics 365 Remote Assist, a mixed reality app that that lets users collaborate during hands-free video calls from their own computers. Organizations have long known the importance of business resiliency, but becoming resilient requires time and preparation, and the pandemic has forced many organizations to evolve at a pace few could have imagined. To recover and thrive within this new context presents new challenges. That is why we are partnering with customers to support faster adoption of digital capabilities.

New Relic sponsored this post. How can you get started with AIOps? What can we expect in the future? A few years ago, Gartner predicted a significant shake-up to ITOps procedures and coined the term "AIOps." It is an evolving solution, based on AI technology, that will revolutionize how IT ecosystems are managed.

Posted by Jason Mayes, Developer Relations Engineer for TensorFlow.js The TensorFlow YouTube channel has a new show called "TensorFlow.js In this program, we highlight amazing tech demos from the TensorFlow.js Our next show will be on 11th December 9AM PT over on the TensorFlow YouTube channel, but if you missed the previous ones, you can find past episodes on this playlist. Do you love great tech demos that push the boundaries of what is possible for a given industry?