In light of the emergence of deep reinforcement learning (DRL) in recommender systems research and several fruitful results in recent years, this survey aims to provide a timely and comprehensive overview of the recent trends of deep reinforcement learning in recommender systems. We start with the motivation of applying DRL in recommender systems. Then, we provide a taxonomy of current DRL-based recommender systems and a summary of existing methods. We discuss emerging topics and open issues, and provide our perspective on advancing the domain. This survey serves as introductory material for readers from academia and industry into the topic and identifies notable opportunities for further research.

Random walk based node embedding algorithms learn vector representations of nodes by optimizing an objective function of node embedding vectors and skip-bigram statistics computed from random walks on the network. They have been applied to many supervised learning problems such as link prediction and node classification and have demonstrated state-of-the-art performance. Yet, their properties remain poorly understood. This paper studies properties of random walk based node embeddings in the unsupervised setting of discovering hidden block structure in the network, i.e., learning node representations whose cluster structure in Euclidean space reflects their adjacency structure within the network. We characterize the ergodic limits of the embedding objective, its generalization, and related convex relaxations to derive corresponding non-randomized versions of the node embedding objectives. We also characterize the optimal node embedding Grammians of the non-randomized objectives for the expected graph of a two-community Stochastic Block Model (SBM). We prove that the solution Grammian has rank $1$ for a suitable nuclear norm relaxation of the non-randomized objective. Comprehensive experimental results on SBM random networks reveal that our non-randomized ergodic objectives yield node embeddings whose distribution is Gaussian-like, centered at the node embeddings of the expected network within each community, and concentrate in the linear degree-scaling regime as the number of nodes increases.

Reliably predicting potential failure risks of machine learning (ML) systems when deployed with production data is a crucial aspect of trustworthy AI. This paper introduces Risk Advisor, a novel post-hoc meta-learner for estimating failure risks and predictive uncertainties of any already-trained black-box classification model. In addition to providing a risk score, the Risk Advisor decomposes the uncertainty estimates into aleatoric and epistemic uncertainty components, thus giving informative insights into the sources of uncertainty inducing the failures. Consequently, Risk Advisor can distinguish between failures caused by data variability, data shifts and model limitations and advise on mitigation actions (e.g., collecting more data to counter data shift). Extensive experiments on various families of black-box classification models and on real-world and synthetic datasets covering common ML failure scenarios show that the Risk Advisor reliably predicts deployment-time failure risks in all the scenarios, and outperforms strong baselines.

Note that there is also a repository of this article with all the resources clearly identified for you to follow in order as well. In my opinion, the best way to start learning anything is with short YouTube video introductions. This field is no exception. There are thousands of amazing videos and playlists that teach important machine learning concepts for free on this platform, and you should definitely take advantage of them. Here, I list a few of the best videos I found that will give you a great first introduction to the terms you need to know to get started in the field.

In social domains, machine learning algorithms often prompt individuals to strategically modify their observable attributes to receive more favorable predictions. As a result, the distribution the predictive model is trained on may differ from the one it operates on in deployment. While such distribution shifts, in general, hinder accurate predictions, we identify a unique opportunity associated with shifts due to strategic responses. In particular, we show that we can use strategic responses effectively to recover causal relationships between observable features and the outcomes we wish to predict. More specifically, we study a game-theoretic model in which a decision-maker deploys a sequence of models to predict an outcome of interest (e.g., college GPA) for a sequence of strategic agents (e.g., college applicants).

Speech recognition technology is finally working for kids. That wasn't the case back in 1999, when my colleagues at Scholastic Education and I launched a reading intervention program called READ 180. We'd hoped to incorporate voice-enabled capabilities: Children would read to a computer program, which would provide real-time feedback on their fluency and literacy. Teachers, in turn, would receive information about their students' progress. Unfortunately, our idea was 20 years ahead of the technology, and we moved ahead with READ 180 without speech-recognition capabilities.

Artificial intelligence was originally conceived as an engineering task. It has now become an important element of all kinds of business and government work, and an integral part of our everyday lives and a variety of jobs. AI education is valuable not only in the fields of computer science and engineering, but also in other sciences, both natural and social, even in the humanities such as the study of literature, history, politics, and in the creative and performing arts. Many educational institutions around the world have decided to integrate AI education into all their offerings, from engineering to business, and the sciences to the humanities, and even the arts. AI has already found applications in many non-traditional areas.

We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. We crafted questions that some humans would answer falsely due to a false belief or misconception. To perform well, models must avoid generating false answers learned from imitating human texts. We tested GPT-3, GPT-Neo/J, GPT-2 and a T5-based model. The best model was truthful on 58% of questions, while human performance was 94%. Models generated many false answers that mimic popular misconceptions and have the potential to deceive humans. The largest models were generally the least truthful. For example, the 6B-parameter GPT-J model was 17% less truthful than its 125M-parameter counterpart. This contrasts with other NLP tasks, where performance improves with model size. However, this result is expected if false answers are learned from the training distribution. We suggest that scaling up models alone is less promising for improving truthfulness than fine-tuning using training objectives other than imitation of text from the web.

Existing question answering (QA) datasets are created mainly for the application of having AI to be able to answer questions asked by humans. But in educational applications, teachers and parents sometimes may not know what questions they should ask a child that can maximize their language learning results. With a newly released book QA dataset (FairytaleQA), which educational experts labeled on 46 fairytale storybooks for early childhood readers, we developed an automated QA generation model architecture for this novel application. Our model (1) extracts candidate answers from a given storybook passage through carefully designed heuristics based on a pedagogical framework; (2) generates appropriate questions corresponding to each extracted answer using a language model; and, (3) uses another QA model to rank top QA-pairs. Automatic and human evaluations show that our model outperforms baselines. We also demonstrate that our method can help with the scarcity issue of the children's book QA dataset via data augmentation on 200 unlabeled storybooks.

The field of artificial intelligence (AI), regarded as one of the most enigmatic areas of science, has witnessed exponential growth in the past decade including a remarkably wide array of applications, having already impacted our everyday lives. Advances in computing power and the design of sophisticated AI algorithms have enabled computers to outperform humans in a variety of tasks, especially in the areas of computer vision and speech recognition. Yet, AI's path has never been smooth, having essentially fallen apart twice in its lifetime ('winters' of AI), both after periods of popular success ('summers' of AI). We provide a brief rundown of AI's evolution over the course of decades, highlighting its crucial moments and major turning points from inception to the present. In doing so, we attempt to learn, anticipate the future, and discuss what steps may be taken to prevent another 'winter'.