Recent years have witnessed the emergence and development of graph neural networks (GNNs), which have been shown as a powerful approach for graph representation learning in many tasks, such as node classification and graph classification. The research on the robustness of these models has also started to attract attentions in the machine learning field. However, most of the existing work in this area focus on the GNNs for node-level tasks, while little work has been done to study the robustness of the GNNs for the graph classification task. In this paper, we aim to explore the vulnerability of the Hierarchical Graph Pooling (HGP) Neural Networks, which are advanced GNNs that perform very well in the graph classification in terms of prediction accuracy. We propose an adversarial attack framework for this task. Specifically, we design a surrogate model that consists of convolutional and pooling operators to generate adversarial samples to fool the hierarchical GNN-based graph classification models. We set the preserved nodes by the pooling operator as our attack targets, and then we perturb the attack targets slightly to fool the pooling operator in hierarchical GNNs so that they will select the wrong nodes to preserve. We show the adversarial samples generated from multiple datasets by our surrogate model have enough transferability to attack current state-of-art graph classification models. Furthermore, we conduct the robust train on the target models and demonstrate that the retrained graph classification models are able to better defend against the attack from the adversarial samples. To the best of our knowledge, this is the first work on the adversarial attack against hierarchical GNN-based graph classification models.

A deep-learning based hybrid strategy for short-term load forecasting is presented. The strategy proposes a novel tree-based ensemble method Warm-start Gradient Tree Boosting (WGTB). Current strategies either ensemble submodels of a single type, which fail to take advantage of statistical strengths of different inference models. Or they simply sum the outputs from completely different inference models, which doesn't maximize the potential of ensemble. WGTB is thus proposed and tailored to the great disparity among different inference models in accuracy, volatility and linearity. The complete strategy integrates four different inference models (i.e., auto-regressive integrated moving average, nu support vector regression, extreme learning machine and long short-term memory neural network), both linear and nonlinear models. WGTB then ensembles their outputs by hybridizing linear estimator ElasticNet and nonlinear estimator ExtraTree via boosting algorithm. It is validated on the real historical data of a grid from State Grid Corporation of China of hourly resolution. The result demonstrates the effectiveness of the proposed strategy that hybridizes statistical strengths of both linear and nonlinear inference models.

In a data-scarce field such as healthcare, where models often deliver predictions on patients with rare conditions, the ability to measure the uncertainty of a model's prediction could potentially lead to improved effectiveness of decision support tools and increased user trust. This work advances the understanding of uncertainty estimation for classification and risk prediction on medical tabular data, in a two-fold way. First, we expand and refine the set of heuristics to select an uncertainty estimation technique, introducing tests for clinically-relevant scenarios such as generalization to uncommon pathologies, changes in clinical protocol and simulations of corrupted data. We furthermore differentiate these heuristics depending on the clinical use-case. Second, we observe that ensembles and related techniques perform poorly when it comes to detecting out-of-domain examples, a critical task which is carried out more successfully by auto-encoders. These remarks are enriched by considerations of the interplay of uncertainty estimation with class imbalance, post-modeling calibration and other modeling procedures. Our findings are supported by an array of experiments on toy and real-world data.

Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself.

Customer experience automation vendor, ActiveCampaign, has secured US$100 million in its latest series B investment round. Key investors this time include Susquehanna and Silversmith Capital Partners, which was the sole sponsor in the series A funding round in 2016. ActiveCampaign said it will use the funding to develop its CXA category through product innovations to advance beyond legacy marketing automation, traditional CRM and service technology, while continuing international expansion and building on its customer success team and partner ecosystem. ActiveCampaign is pitching its platform across the spectrum of small, midsize, and enterprise businesses and has 90,000 customers spanning 161 countries. Since its last funding round, the company said it had increased annual recurring revenue six-fold to more than $90 million, opened new offices in several locations including Sydney, and grown its employee base to 550 staff.

In modern-day marketing, artificial intelligence (AI) plays a prominent role. AI has become an essential part of digital marketing strategies, and it has proven to be a successful tool. Marketers are willing to use AI more and more as this intelligent tool makes life easy for them. Adapting is key to running a successful business in the digital world, and the AI wave has hit all the major companies, making them more productive and making customer business relationships easy. This article will break down a few pointers on the positive impact AI has had on marketers and the Digital Marketing industry.

In a previous blog post, I covered some of the challenges encountered by security operations centers (SOCs) and how leveraging artificial intelligence (AI) can help alleviate these challenges, including the cybersecurity skills shortage, unaddressed security risks and long dwell times. According to ISACA's State of Cybersecurity Report, 78 percent of respondents expect the demand for technical cybersecurity roles to increase in the future. The report also mentions that the effects of the skills shortage are going to get worse. This is where AI can step in and help lighten the load considerably. During a time of tight budgets and IT spend, there is no doubt that any new expenditures must have solid business justifications.

The transport sector expects a great deal from the air. Air transport has remained more or less stable over the last decades. However, technological innovations emerging in various areas, are threatening to change this scenario. This is illustrated, for example, with the steps taken towards making flying taxis a reality. Airports are aware of this situation.

Before and even more so now during the pandemic, CIOs and IT leaders are managing new capacity increases, security demands, and, in some cases critical, life-saving applications. It is essential how optimized technological performance enables the digital applications that power daily lives. AppDynamics, a Cisco company, helps companies around the world power their complex multi-cloud environments, through application performance management (APM) and Artificial Intelligence for IT operations (AIOps). I asked Luke Rogers, Area VP, Canada, AppDynamics, how COVID-19 has impacted businesses. "The COVID-19 pandemic has transformed our everyday interactions and how companies operate," replied Rogers.

Governor Northam announced that Virginians can now use COVIDCheck, a new online risk-assessment tool to check their symptoms and connect with the appropriate health care resource, including COVID-19 testing. "If you are feeling sick or think you may have been exposed to someone with COVID-19, it is important that you take action right away," said Governor Northam. "This online symptom-checking tool can help Virginians understand their personal risk for COVID-19 and get recommendations about what to do next from the safety of their homes. As we work to flatten the curve in our Commonwealth, telehealth services like this will be vital to relieving some of the strains on providers and health systems and making health care more convenient and accessible." COVIDCheck is a free, web-based, artificial intelligence-powered telehealth tool that can help individuals displaying symptoms associated with COVID-19 self-assess their risk and determine the best next steps, such as self-isolation, seeing a doctor, or seeking emergency care.