Unsupervised graph-level representation learning plays a crucial role in a variety of tasks such as molecular property prediction and community analysis, especially when data annotation is expensive. Currently, most of the best-performing graph embedding methods are based on Infomax principle. The performance of these methods highly depends on the selection of negative samples and hurt the performance, if the samples were not carefully selected. Inter-graph similarity-based methods also suffer if the selected set of graphs for similarity matching is low in quality. To address this, we focus only on utilizing the current input graph for embedding learning. We are motivated by an observation from real-world graph generation processes where the graphs are formed based on one or more global factors which are common to all elements of the graph (e.g., topic of a discussion thread, solubility level of a molecule). We hypothesize extracting these common factors could be highly beneficial. Hence, this work proposes a new principle for unsupervised graph representation learning: Graph-wise Common latent Factor EXtraction (GCFX). We further propose a deep model for GCFX, deepGCFX, based on the idea of reversing the above-mentioned graph generation process which could explicitly extract common latent factors from an input graph and achieve improved results on downstream tasks to the current state-of-the-art. Through extensive experiments and analysis, we demonstrate that, while extracting common latent factors is beneficial for graph-level tasks to alleviate distractions caused by local variations of individual nodes or local neighbourhoods, it also benefits node-level tasks by enabling long-range node dependencies, especially for disassortative graphs.

Long-range transformer models have achieved encouraging results on long-context question answering (QA) tasks. Such tasks often require reasoning over a long document, and they benefit from identifying a set of evidence spans (e.g., sentences) that provide supporting evidence for addressing the question. In this work, we propose a novel method for equipping long-range transformers with an additional sequence-level objective for better identification of supporting evidence spans. We achieve this by proposing an additional contrastive supervision signal in finetuning, where the model is encouraged to explicitly discriminate supporting evidence sentences from negative ones by maximizing the question-evidence similarity. The proposed additional loss exhibits consistent improvements on three different strong long-context transformer models, across two challenging question answering benchmarks - HotpotQA and QAsper.

Monumental advances in deep learning have led to unprecedented achievements across a multitude of domains. While the performance of deep neural networks is indubitable, the architectural design and interpretability of such models are nontrivial. Research has been introduced to automate the design of neural network architectures through neural architecture search (NAS). Recent progress has made these methods more pragmatic by exploiting distributed computation and novel optimization algorithms. However, there is little work in optimizing architectures for interpretability. To this end, we propose a multi-objective distributed NAS framework that optimizes for both task performance and introspection. We leverage the non-dominated sorting genetic algorithm (NSGA-II) and explainable AI (XAI) techniques to reward architectures that can be better comprehended by humans. The framework is evaluated on several image classification datasets. We demonstrate that jointly optimizing for introspection ability and task error leads to more disentangled architectures that perform within tolerable error.

"In the 21st century, it is wise to invest in various sectors. So, are you searching for AI companies to invest, in Australia? Electrum IT Solutions Pvt. Ltd. is currently one of the popular Information Technology & Services companies. It is a company worth investing in for the evident reason. You might have some queries that need some answers.

Australia's National Artificial Intelligence Centre has been launched to help unlock the potential of AI for business by coordinating the country's AI expertise and capabilities. The Centre is part of the federal government's $124.1 million investment under its AI Action Plan, which sets out a vision for Australia to become a global leader in developing and adopting trusted, secure and responsible artificial intelligence. Minister for Science and Technology Melissa Price said the Government was delivering on the AI Action Plan, ensuring Australia was charging ahead in developing and adopting artificial intelligence products and services. "The launch of the National Artificial Intelligence Centre positions Australia as a global leader in AI technology, harnessing our collective capabilities, talent and resources to be developers and drive early adoption of AI by our businesses," Minister Price said. "The National Artificial Intelligence Centre will play a pivotal role in ensuring we can take advantage of AI technologies, which has been forecast to contribute more than $20 trillion to the global economy by 2030. It will unlock the potential of AI and create new opportunities for business to access critical AI expertise and capabilities. The National Artificial Intelligence Centre will also help address barriers that small and medium enterprises face in developing AI and other emerging technologies by connecting business with the talent, knowledge and tools to succeed."

In October, the Forum for Cooperation on Artificial Intelligence (FCAI), a multistakeholder dialogue among high-level government officials and experts from industry, civil society, and academia, released an interim report taking stock of the current landscape for international cooperation on AI and offering recommendations to make further progress. FCAI publicly launched the report as part of Brookings' Global Forum on Democracy and Technology event, Aligning technology governance with democratic values. UK Secretary of State Digital, Culture, Media and Sport, Nadine Dorries, praised the "excellent" report as a "helpful step in [the] process" of building international AI collaboration while discussing her government's role in its presidency of the G7 group and its upcoming Future Tech Forum. To discuss the report, Brookings co-authors Cam Kerry and Josh Meltzer, and Andrea Renda of the Centre for European Policy Studies (CEPS) welcomed a panel featuring representatives from the governments of Australia, Canada, and the United States, as well as industry representatives from IBM and Twitter. While the entire event and panel discussion around the report can be found here, for some unfamiliar with the FCAI, this blog will serve as an introduction to the Forum and the new report.

Machine learning (ML) methodology, fueled with access to ever-increasing masses of data and unprecedented computing power, has been the main driving factor of recent progress in artificial intelligence (AI) and its applications in various branches of science and technology, industry and business, economics and finance, amongst others. In this regard, ML is most commonly perceived as a means for predictive modeling, that is, for the data-driven construction of a model that is mainly used for the purpose of predicting unknown facts in a specific context -- albeit models may, of course, serve other purposes, too, such as understanding and explanation, or may have a more descriptive flavor. A predictive model, or "predictor" in ML jargon, is trained in a supervised manner on cases encountered by the "learner" over the course of time, such as emails categorized as spam or non-spam, and the model is then used to make predictions in future situations, e.g., to automatically mark new emails. Looking at emerging applications of ML methodology, there is a visible shift from predictive modeling to prescriptive modeling, by which we mean the task of learning a model that stipulates appropriate decisions or actions to be taken in real-world scenarios. In fact, decisions are nowadays increasingly automated and made by algorithms instead of humans, and most of these automated decision making (ADM) algorithms are trained on data using ML methods. For example, think of decisions in the context of employees recruitment, such as hiring or placement decisions [41].

There is an ongoing debate in the NLP community whether modern language models contain linguistic knowledge, recovered through so-called probes. In this paper, we study whether linguistic knowledge is a necessary condition for the good performance of modern language models, which we call the rediscovery hypothesis. In the first place, we show that language models that are significantly compressed but perform well on their pretraining objectives retain good scores when probed for linguistic structures. This result supports the rediscovery hypothesis and leads to the second contribution of our paper: an information-theoretic framework that relates language modeling objectives with linguistic information. This framework also provides a metric to measure the impact of linguistic information on the word prediction task. We reinforce our analytical results with various experiments, both on synthetic and on real NLP tasks in English.

Astronomical transients are stellar objects that become temporarily brighter on various timescales and have led to some of the most significant discoveries in cosmology and astronomy. Some of these transients are the explosive deaths of stars known as supernovae while others are rare, exotic, or entirely new kinds of exciting stellar explosions. New astronomical sky surveys are observing unprecedented numbers of multi-wavelength transients, making standard approaches of visually identifying new and interesting transients infeasible. To meet this demand, we present two novel methods that aim to quickly and automatically detect anomalous transient light curves in real-time. Both methods are based on the simple idea that if the light curves from a known population of transients can be accurately modelled, any deviations from model predictions are likely anomalies. The first approach is a probabilistic neural network built using Temporal Convolutional Networks (TCNs) and the second is an interpretable Bayesian parametric model of a transient. We show that the flexibility of neural networks, the attribute that makes them such a powerful tool for many regression tasks, is what makes them less suitable for anomaly detection when compared with our parametric model.

Agent-based and activity-based models for simulating transportation systems have attracted significant attention in recent years. Few studies, however, include a detailed representation of active modes of transportation - such as walking and cycling - at a city-wide level, where dominating motorised modes are often of primary concern. This paper presents an open workflow for creating a multi-modal agent-based and activity-based transport simulation model, focusing on Greater Melbourne, and including the process of mode choice calibration for the four main travel modes of driving, public transport, cycling and walking. The synthetic population generated and used as an input for the simulation model represented Melbourne's population based on Census 2016, with daily activities and trips based on the Victoria's 2016-18 travel survey data. The road network used in the simulation model includes all public roads accessible via the included travel modes. We compared the output of the simulation model with observations from the real world in terms of mode share, road volume, travel time, and travel distance. Through these comparisons, we showed that our model is suitable for studying mode choice and road usage behaviour of travellers.