In recent years, transformer models have revolutionized Natural Language Processing (NLP) and also show promising performance on Computer Vision (CV) tasks. Despite their effectiveness, transformers' attention operations are hard to accelerate due to complicated data movement and quadratic computational complexity, prohibiting the real-time inference on resource-constrained edge-computing platforms. To tackle this challenge, we propose Energon, an algorithm-architecture co-design approach that accelerates various transformers using dynamic sparse attention. With the observation that attention results only depend on a few important query-key pairs, we propose a multi-round filtering algorithm to dynamically identify such pairs at runtime. We adopt low bitwidth in each filtering round and only use high-precision tensors in the attention stage to reduce overall complexity. By this means, we significantly mitigate the computational cost with negligible accuracy loss. To enable such an algorithm with lower latency and better energy-efficiency, we also propose an Energon co-processor architecture. Elaborated pipelines and specialized optimizations jointly boost the performance and reduce power consumption. Extensive experiments on both NLP and CV benchmarks demonstrate that Energon achieves $161\times$ and $8.4\times$ geo-mean speedup and up to $10^4\times$ and $10^3\times$ energy reduction compared with Intel Xeon 5220 CPU and NVIDIA V100 GPU. Compared to state-of-the-art attention accelerators SpAtten and $A^3$, Energon also achieves $1.7\times, 1.25\times$ speedup and $1.6 \times, 1.5\times $ higher energy efficiency.

We present an approach for representing abstract argumentation frameworks based on an encoding into classical higher-order logic. This provides a uniform framework for computer-assisted assessment of abstract argumentation frameworks using interactive and automated reasoning tools. This enables the formal analysis and verification of meta-theoretical properties as well as the flexible generation of extensions and labellings with respect to well-known argumentation semantics.

Improving the resilience of a network protects the system from natural disasters and malicious attacks. This is typically achieved by introducing new edges, which however may reach beyond the maximum number of connections a node could sustain. Many studies then resort to the degree-preserving operation of rewiring, which swaps existing edges $AC, BD$ to new edges $AB, CD$. A significant line of studies focuses on this technique for theoretical and practical results while leaving three limitations: network utility loss, local optimality, and transductivity. In this paper, we propose ResiNet, a reinforcement learning (RL)-based framework to discover resilient network topologies against various disasters and attacks. ResiNet is objective agnostic which allows the utility to be balanced by incorporating it into the objective function. The local optimality, typically seen in greedy algorithms, is addressed by casting the cumulative resilience gain into a sequential decision process of step-wise rewiring. The transductivity, which refers to the necessity to run a computationally intensive optimization for each input graph, is lifted by our variant of RL with auto-regressive permutation-invariant variable action space. ResiNet is armed by our technical innovation, Filtration enhanced GNN (FireGNN), which distinguishes graphs with minor differences. It is thus possible for ResiNet to capture local structure changes and adapt its decision among consecutive graphs, which is known to be infeasible for GNN. Extensive experiments demonstrate that with a small number of rewiring operations, ResiNet achieves a near-optimal resilience gain on multiple graphs while balancing the utility, with a large margin compared to existing approaches.

At the core of statistical learning lies the problem of understanding the generalization performance (e.g., out-of-sample errors) of the learning algorithms in use. Conventional wisdom in statistics held that including too many covariates when training statistical models can hurt generalization (despite improving training accuracy), due to the undesired over-fit. This leads to the classical conclusion that: proper regularization -- through either adding certain penalty functions to the loss function or algorithmic self-regularization -- seems to be critical in achieving the desired accuracy (e.g., Friedman et al. (2001); Wei et al. (2019)). However, an evolving line of works in machine learning observes empirical evidence that suggests, to the surprise of many statisticians, over-parameterization is not necessarily harmful. Indeed, many machine learning models (such as random forests or deep neural networks) are trained until the training error vanishes to zero -- meaning that they are able to perfectly interpolate the data -- while still generalizing well (e.g., Zhang et al. (2021); Wyner et al. (2017); Belkin et al. (2019)). As a key observation to explain this phenomenon, many models when trained by gradient type methods (e.g., gradient descent, stochastic gradient descent, AdaBoost) converge to certain minimum norm interpolators, which implicitly favor models with smaller model complexity. These empirical mysteries inspire a recent flurry of activity towards understanding the generalization properties of various interpolators.

The Delta variant of the coronavirus spread to more countries in recent weeks, and the total number of cases officially logged soared past half a million per day. The global number of deaths is now about two-thirds as high as it was at the peak of the previous wave, in April of this year. As the virus spreads, the potential rises for a vaccine-resistant strain to emerge. Meanwhile, in poorer countries, vaccines are scarce, and most populations are little protected (exhibit).

Every October for the last four decades, Breast Cancer Awareness Month has helped to raise visibility of the most prevalent cancer on Earth -- one that takes almost three-quarters of a million lives every year. Despite recorded cases stretching back to ancient Egypt, breast cancer was considered an "unspeakable" condition for millennia. Women were expected to suffer in silence and "dignity." This stigma fueled academic ignorance, with breast cancer languishing as a relatively unstudied disease until just a few decades ago. For most of the last century, a woman suffering from breast cancer would be offered radiation therapy and/or surgery -- often radical surgery, leaving them disfigured for little benefit -- while the treatment of other cancers progressed.

Big data has remarkably evolved over the last few years to realize an enormous volume of data generated from newly emerging services and applications and a massive number of Internet-of-Things (IoT) devices. The potential of big data can be realized via analytic and learning techniques, in which the data from various sources is transferred to a central cloud for central storage, processing, and training. However, this conventional approach faces critical issues in terms of data privacy as the data may include sensitive data such as personal information, governments, banking accounts. To overcome this challenge, federated learning (FL) appeared to be a promising learning technique. However, a gap exists in the literature that a comprehensive survey on FL for big data services and applications is yet to be conducted. In this article, we present a survey on the use of FL for big data services and applications, aiming to provide general readers with an overview of FL, big data, and the motivations behind the use of FL for big data. In particular, we extensively review the use of FL for key big data services, including big data acquisition, big data storage, big data analytics, and big data privacy preservation. Subsequently, we review the potential of FL for big data applications, such as smart city, smart healthcare, smart transportation, smart grid, and social media. Further, we summarize a number of important projects on FL-big data and discuss key challenges of this interesting topic along with several promising solutions and directions.

AI surveillance is increasing at a rapid pace around the world. The East Asia/Pacific, Americas, and the Middle East/North Africa regions are robust adopters of these tools. Even liberal democracies in Europe have installed automated border controls, predictive policing, "safe cities", and facial recognition systems. China is the biggest supplier of these technologies which can be found in 63 countries. Huawei alone is responsible for providing AI surveillance technology to at least fifty countries and its leadership has strong ties with the Chinese government.

AI that understands the world from a first-person point of view could unlock a new era of immersive experiences, as devices like augmented reality (AR) glasses and virtual reality (VR) headsets become as useful in everyday life as smartphones. Imagine your AR device displaying exactly how to hold the sticks during a drum lesson, guiding you through a recipe, helping you find your lost keys, or recalling memories as holograms that come to life in front of you. To build these new technologies, we need to teach AI to understand and interact with the world like we do, from a first-person perspective -- commonly referred to in the research community as egocentric perception. Today's computer vision (CV) systems, however, typically learn from millions of photos and videos that are captured in third-person perspective, where the camera is just a spectator to the action. "Next-generation AI systems will need to learn from an entirely different kind of data -- videos that show the world from the center of the action, rather than the sidelines," says Kristen Grauman, lead research scientist at Facebook.

Eighty-five percent of the world's population lives in areas impacted by human-induced climate change, according to an international team of researchers. They used a new machine learning approach to identify more than 100,000 scientific studies on the effects of climate change across every continent. This massive literature review created a global map of impacts, which the team then compared to changing trends of surface temperature and rain caused by humans. In the age of big data, using AI is an important tool for climate scientists, the researchers say. While it can't substitute for expert assessments like the Intergovernmental Panel on Climate Change (IPPC), using machine learning to sort through climate studies is invaluable to helping map evidence in a systematic way.