As the world's largest professional network, LinkedIn wants to create economic opportunity for everyone in the global workforce. One of its most critical missions is matching jobs with processionals. Improving job targeting accuracy and hire efficiency align with LinkedIn's Member First Motto. To achieve those goals, we need to understand unstructured job postings with noisy information. We applied deep transfer learning to create domain-specific job understanding models. After this, jobs are represented by professional entities, including titles, skills, companies, and assessment questions. To continuously improve LinkedIn's job understanding ability, we designed an expert feedback loop where we integrated job understanding models into LinkedIn's products to collect job posters' feedback. In this demonstration, we present LinkedIn's job posting flow and demonstrate how the integrated deep job understanding work improves job posters' satisfaction and provides significant metric lifts in LinkedIn's job recommendation system.

This paper provides a graphical characterization of Markov blankets in chain graphs (CGs) under the Lauritzen-Wermuth-Frydenberg (LWF) interpretation. The characterization is different from the well-known one for Bayesian networks and generalizes it. We provide a novel scalable and sound algorithm for Markov blanket discovery in LWF CGs and prove that the Grow-Shrink algorithm, the IAMB algorithm, and its variants are still correct for Markov blanket discovery in LWF CGs under the same assumptions as for Bayesian networks. We provide a sound and scalable constraint-based framework for learning the structure of LWF CGs from faithful causally sufficient data and prove its correctness when the Markov blanket discovery algorithms in this paper are used. Our proposed algorithms compare positively/competitively against the state-of-the-art LCD (Learn Chain graphs via Decomposition) algorithm, depending on the algorithm that is used for Markov blanket discovery. Our proposed algorithms make a broad range of inference/learning problems computationally tractable and more reliable because they exploit locality.

As ML applications are becoming ever more pervasive, fully-trained systems are made increasingly available to a wide public, allowing end-users to submit queries with their own data, and to efficiently retrieve results. With increasingly sophisticated such services, a new challenge is how to scale up to evergrowing user bases. In this paper, we present a distributed architecture that could be exploited to parallelize a typical ML system pipeline. We propose a case study consisting of a text mining service and discuss how the method can be generalized to many similar applications. We demonstrate the significance of the computational gain boosted by the distributed architecture by way of an extensive experimental evaluation.

Serverless computing has emerged as a compelling new paradigm of cloud computing models in recent years. It promises the user services at large scale and low cost while eliminating the need for infrastructure management. On cloud provider side, flexible resource management is required to meet fluctuating demand. It can be enabled through automated provisioning and deprovisioning of resources. A common approach among both commercial and open source serverless computing platforms is workload-based auto-scaling, where a designated algorithm scales instances according to the number of incoming requests. In the recently evolving serverless framework Knative a request-based policy is proposed, where the algorithm scales resources by a configured maximum number of requests that can be processed in parallel per instance, the so-called concurrency. As we show in a baseline experiment, this predefined concurrency level can strongly influence the performance of a serverless application. However, identifying the concurrency configuration that yields the highest possible quality of service is a challenging task due to various factors, e.g. varying workload and complex infrastructure characteristics, influencing throughput and latency. While there has been considerable research into intelligent techniques for optimizing auto-scaling for virtual machine provisioning, this topic has not yet been discussed in the area of serverless computing. For this reason, we investigate the applicability of a reinforcement learning approach, which has been proven on dynamic virtual machine provisioning, to request-based auto-scaling in a serverless framework. Our results show that within a limited number of iterations our proposed model learns an effective scaling policy per workload, improving the performance compared to the default auto-scaling configuration.

With advances in reinforcement learning (RL), agents are now being developed in high-stakes application domains such as healthcare and transportation. Explaining the behavior of these agents is challenging, as the environments in which they act have large state spaces, and their decision-making can be affected by delayed rewards, making it difficult to analyze their behavior. To address this problem, several approaches have been developed. Some approaches attempt to convey the $\textit{global}$ behavior of the agent, describing the actions it takes in different states. Other approaches devised $\textit{local}$ explanations which provide information regarding the agent's decision-making in a particular state. In this paper, we combine global and local explanation methods, and evaluate their joint and separate contributions, providing (to the best of our knowledge) the first user study of combined local and global explanations for RL agents. Specifically, we augment strategy summaries that extract important trajectories of states from simulations of the agent with saliency maps which show what information the agent attends to. Our results show that the choice of what states to include in the summary (global information) strongly affects people's understanding of agents: participants shown summaries that included important states significantly outperformed participants who were presented with agent behavior in a randomly set of chosen world-states. We find mixed results with respect to augmenting demonstrations with saliency maps (local information), as the addition of saliency maps did not significantly improve performance in most cases. However, we do find some evidence that saliency maps can help users better understand what information the agent relies on in its decision making, suggesting avenues for future work that can further improve explanations of RL agents.

Bayesian optimization is a broadly applied methodology to optimize the expensive blackbox function. Despite its success, it still faces the challenge from the high-dimensional search space. To alleviate this problem, we propose a novel Bayesian optimization framework, which finds a low-dimensional space to perform Bayesian optimization through a semi-supervised, iterative, and embedding learning-based method (SILBO). SILBO incorporates both labeled and unlabeled points acquired from the acquisition function of Bayesian optimization to guide the learning of embedding space. To accelerate the learning procedure, we present a randomized method for generating the projection matrix. Furthermore, to map from the low-dimensional space to the high-dimensional original space, we propose two mapping strategies: SILBO-BU and SILBO-TD according to the evaluation overhead of the objective function. Experimental results on both synthetic function and hyperparameter optimization tasks demonstrate that SILBO outperforms the existing state-of-the-art high-dimensional Bayesian optimization methods.

We describe several datasets and first experiments with creating conjectures by neural methods. The datasets are based on the Mizar Mathematical Library processed in several forms and the problems extracted from it by the MPTP system and proved by the E prover using the ENIGMA guidance. The conjecturing experiments use the Transformer architecture and in particular its GPT-2 implementation.

Framed in positive terms, this report examines how technical AI research might be steered in a manner that is more attentive to humanity's long-term prospects for survival as a species. In negative terms, we ask what existential risks humanity might face from AI development in the next century, and by what principles contemporary technical research might be directed to address those risks. A key property of hypothetical AI technologies is introduced, called \emph{prepotence}, which is useful for delineating a variety of potential existential risks from artificial intelligence, even as AI paradigms might shift. A set of \auxref{dirtot} contemporary research \directions are then examined for their potential benefit to existential safety. Each research direction is explained with a scenario-driven motivation, and examples of existing work from which to build. The research directions present their own risks and benefits to society that could occur at various scales of impact, and in particular are not guaranteed to benefit existential safety if major developments in them are deployed without adequate forethought and oversight. As such, each direction is accompanied by a consideration of potentially negative side effects.

Knowledge graphs (KGs) have become the preferred technology for representing, sharing and adding knowledge to modern AI applications. While KGs have become a mainstream technology, the RDF/SPARQL-centric toolset for operating with them at scale is heterogeneous, difficult to integrate and only covers a subset of the operations that are commonly needed in data science applications. In this paper, we present KGTK, a data science-centric toolkit to represent, create, transform, enhance and analyze KGs. KGTK represents graphs in tables and leverages popular libraries developed for data science applications, enabling a wide audience of developers to easily construct knowledge graph pipelines for their applications. We illustrate KGTK with real-world scenarios in which we have used KGTK to integrate and manipulate large KGs, such as Wikidata, DBpedia and ConceptNet, in our own work.

Most machine learning models, especially artificial neural networks, require numerical, not categorical data. We briefly describe the advantages and disadvantages of common encoding schemes. For example, one-hot encoding is commonly used for attributes with a few unrelated categories and word embeddings for attributes with many related categories (e.g., words). Neither is suitable for encoding attributes with many unrelated categories, such as diagnosis codes in healthcare applications. Application of one-hot encoding for diagnosis codes, for example, can result in extremely high dimensionality with low sample size problems or artificially induce machine learning artifacts, not to mention the explosion of computing resources needed. Quasi-orthonormal encoding (QOE) fills the gap. We briefly show how QOE compares to one-hot encoding. We provide example code of how to implement QOE using popular ML libraries such as Tensorflow and PyTorch and a demonstration of QOE to MNIST handwriting samples.