Dynamic networks are used in a wide range of fields, including social network analysis, recommender systems and epidemiology. Representing complex networks as structures changing over time allow network models to leverage not only structural but also temporal patterns. However, as dynamic network literature stems from diverse fields and makes use of inconsistent terminology, it is challenging to navigate. Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification. Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. We aim to provide a review that demystifies dynamic networks, introduces dynamic graph neural networks (DGNNs) and appeals to researchers with a background in either network science or data science. We contribute: (i) a comprehensive dynamic network taxonomy, (ii) a survey of dynamic graph neural networks and (iii) an overview of how dynamic graph neural networks can be used for dynamic link prediction.

Machine learning models with both good predictability and high interpretability are crucial for decision support systems. Linear regression is one of the most interpretable prediction models. However, the linearity in a simple linear regression worsens its predictability. In this work, we introduce a locally adaptive interpretable regression (LoAIR). In LoAIR, a metamodel parameterized by neural networks predicts percentile of a Gaussian distribution for the regression coefficients for a rapid adaptation. Our experimental results on public benchmark datasets show that our model not only achieves comparable or better predictive performance than the other state-of-the-art baselines but also discovers some interesting relationships between input and target variables such as a parabolic relationship between CO2 emissions and Gross National Product (GNP). Therefore, LoAIR is a step towards bridging the gap between econometrics, statistics, and machine learning by improving the predictive ability of linear regression without depreciating its interpretability.

The travelling thief problem (TTP) is a multi-component optimisation problem involving two interdependent NP-hard components: the travelling salesman problem (TSP) and the knapsack problem (KP). Recent state-of-the-art TTP solvers modify the underlying TSP and KP solutions in an iterative and interleaved fashion. The TSP solution (cyclic tour) is typically changed in a deterministic way, while changes to the KP solution typically involve a random search, effectively resulting in a quasi-meandering exploration of the TTP solution space. Once a plateau is reached, the iterative search of the TTP solution space is restarted by using a new initial TSP tour. We propose to make the search more efficient through an adaptive surrogate model (based on a customised form of Support Vector Regression) that learns the characteristics of initial TSP tours that lead to good TTP solutions. The model is used to filter out non-promising initial TSP tours, in effect reducing the amount of time spent to find a good TTP solution. Experiments on a broad range of benchmark TTP instances indicate that the proposed approach filters out a considerable number of non-promising initial tours, at the cost of omitting only a small number of the best TTP solutions.

We introduce BIOMRC, a large-scale cloze-style biomedical MRC dataset. Care was taken to reduce noise, compared to the previous BIOREAD dataset of Pappas et al. (2018). Experiments show that simple heuristics do not perform well on the new dataset, and that two neural MRC models that had been tested on BIOREAD perform much better on BIOMRC, indicating that the new dataset is indeed less noisy or at least that its task is more feasible. Non-expert human performance is also higher on the new dataset compared to BIOREAD, and biomedical experts perform even better. We also introduce a new BERT-based MRC model, the best version of which substantially outperforms all other methods tested, reaching or surpassing the accuracy of biomedical experts in some experiments. We make the new dataset available in three different sizes, also releasing our code, and providing a leaderboard.

This is the AI Song Contest, where thirteen teams from Europe and Australia compete for the title of the best song created using artificial intelligence. The teams have been working overtime lately, hunched over their computers to create the ultimate Eurovision hit with the help of artificial intelligence. The best track as chosen by the audience and AI experts will be unveiled in this festive live stream. Who will scoop up douze points and win the AI Song Contest 2020? The AI Song Contest researches the creative possibilities of artificial intelligence and is organised by Dutch public broadcaster VPRO in collaboration with NPO 3FM and NPO Innovation.

The UK's job retention scheme, which pays 80 per cent of furloughed employees' wages up to £2500 a month, will be extended for four months until October. Rishi Sunak, the chancellor of the exchequer, said that from August employees will be allowed to work part-time while furloughed, but the government will require companies to shoulder some of the costs of furlough payments. The scheme currently covers the salaries of 7.5 million workers, a quarter of the UK's workforce, and costs the UK government about £14 billion a month. Head teachers have warned that the government's plan to reopen schools for some year groups in England on 1 June is not feasible. Paul Whiteman, head of the National Association for Head Teachers, told MPs that it wouldn't be possible to comply with the government's new guidance recommending a maximum class size of 15 pupils. Northern Ireland has unveiled a five-stage plan for easing coronavirus restrictions, which includes advice for specific job sectors and is ...

People in England can return to work if they can't work from home Restrictions to curb the spread of coronavirus are being eased slightly in England this week, but many have criticised the government for creating confusion with a new slogan telling people to "stay alert", which replaces previous advice to "stay at home." In a video message broadcast on Sunday evening, prime minister Boris Johnson announced the following changes to the government's policy in England, which are listed in full online and will come into effect from Wednesday 13 May: These new policies mean that social distancing rules in England are now different from the advice given to UK citizens in Scotland, Wales and Northern Ireland. Scotland's first minister Nicola Sturgeon said people should continue to "stay at home", and Northern Ireland's first minister Arlene Foster also rejected the new slogan. Some London Underground platforms were packed with passengers this morning following last night's announcement.

Emotion lexicons describe the affective meaning of words and thus constitute a centerpiece for advanced sentiment and emotion analysis. Yet, manually curated lexicons are only available for a handful of languages, leaving most languages of the world without such a precious resource for downstream applications. Even worse, their coverage is often limited both in terms of the lexical units they contain and the emotional variables they feature. In order to break this bottleneck, we here introduce a methodology for creating almost arbitrarily large emotion lexicons for any target language. Our approach requires nothing but a source language emotion lexicon, a bilingual word translation model, and a target language embedding model. Fulfilling these requirements for 91 languages, we are able to generate representationally rich high-coverage lexicons comprising eight emotional variables with more than 100k lexical entries each. We evaluated the automatically generated lexicons against human judgment from 26 datasets, spanning 12 typologically diverse languages, and found that our approach produces results in line with state-of-the-art monolingual approaches to lexicon creation and even surpasses human reliability for some languages and variables. Code and data are available at https://github.com/JULIELab/MEmoLon archived under DOI https://doi.org/10.5281/zenodo.3779901.

Artificial Intelligence (AI) is being increasingly used to develop systems that produce intelligent solutions. However, there is a major concern that whether the systems built will be trusted by humans. In order to establish trust in AI systems, there is a need for the user to understand the reasoning behind their solutions and therefore, the system should be able to explain and justify its output. In this paper, we use argumentation to provide explanations in the domain of AI planning. We present argument schemes to create arguments that explain a plan and its components; and a set of critical questions that allow interaction between the arguments and enable the user to obtain further information regarding the key elements of the plan. Finally, we present some properties of the plan arguments.

For many ASEAN nations, manufacturing takes up a sizable chunk of the national GDP. For example, manufacturing in Singapore contributed 20.9 percent of Singapore's GDP in 2019, according to the department of statistics Singapore. Successful companies readily acknowledge one key factor contributing to their achievements – hardworking, committed and skilled employees who are the foundation of the companies. However, manufacturers today face the primary challenge of filling open positions with skilled workers, which in turn affects overall productivity and growth. In addition to the human capital challenge, manufacturers are facing immense costs associated with workplace injuries.