The dream of endowing computers with causal reasoning drew Bareinboim from Brazil to the United States in 2008, after he completed a master's in computer science at the Federal University of Rio de Janeiro. He jumped at an opportunity to study under Judea Pearl, a computer scientist and statistician at UCLA. Pearl, 83, is a giant--the giant--of causal inference, and his career helps illustrate why it's hard to create AI that understands causality.

In this study we focus on the prediction of basketball games in the Euroleague competition using machine learning modelling. The prediction is a binary classification problem, predicting whether a match finishes 1 (home win) or 2 (away win). Data is collected from the Euroleague's official website for the seasons 2016-2017, 2017-2018 and 2018-2019, i.e. in the new format era. Features are extracted from matches' data and off-the-shelf supervised machine learning techniques are applied. We calibrate and validate our models. We find that simple machine learning models give accuracy not greater than 67% on the test set, worse than some sophisticated benchmark models. Additionally, the importance of this study lies in the "wisdom of the basketball crowd" and we demonstrate how the predicting power of a collective group of basketball enthusiasts can outperform machine learning models discussed in this study. We argue why the accuracy level of this group of "experts" should be set as the benchmark for future studies in the prediction of (European) basketball games using machine learning.

Knowledge bases (KBs) have gradually become a valuable asset for many AI applications. While many current KBs are quite large, they are widely acknowledged as incomplete, especially lacking facts of long-tail entities, e.g., less famous persons. Existing approaches enrich KBs mainly on completing missing links or filling missing values. However, they only tackle a part of the enrichment problem and lack specific considerations regarding long-tail entities. In this paper, we propose a full-fledged approach to knowledge enrichment, which predicts missing properties and infers true facts of long-tail entities from the open Web. Prior knowledge from popular entities is leveraged to improve every enrichment step. Our experiments on the synthetic and real-world datasets and comparison with related work demonstrate the feasibility and superiority of the approach.

We introduce a method called TrackIn that computes the influence of a training example on a prediction made by the model, by tracking how the loss on the test point changes during the training process whenever the training example of interest was utilized. We provide a scalable implementation of TrackIn via a combination of a few key ideas: (a) a first-order approximation to the exact computation, (b) using random projections to speed up the computation of the first-order approximation for large models, (c) using saved checkpoints of standard training procedures, and (d) cherry-picking layers of a deep neural network. An experimental evaluation shows that TrackIn is more effective in identifying mislabelled training examples than other related methods such as influence functions and representer points. We also discuss insights from applying the method on vision, regression and natural language tasks.

Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are implemented as large Discrete Fourier Transform matrices; which are prohibitively inefficient for low-compute systems. We present an efficient, trainable front-end based on the butterfly mechanism to compute the Fast Fourier Transform, and show its accuracy and efficiency benefits for low-compute neural speech enhancement models. We also explore the effects of making the STFT window trainable.

Graph neural networks aggregate features in vertex neighborhoods to learn vector representations of all vertices, using supervision from some labeled vertices during training. The predictor is then a function of the vector representation, and predictions are made independently on unlabeled nodes. This widely-adopted approach implicitly assumes that vertex labels are independent after conditioning on their neighborhoods. We show that this strong assumption is far from true on many real-world graph datasets and severely limits predictive power on a number of regression tasks. Given that traditional graph-based semi-supervised learning methods operate in the opposite manner by explicitly modeling the correlation in predicted outcomes, this limitation may not be all that surprising. Here, we address this issue with a simple and interpretable framework that can improve any graph neural network architecture by modeling correlation structure in regression outcome residuals. Specifically, we model the joint distribution of outcome residuals on vertices with a parameterized multivariate Gaussian, where the parameters are estimated by maximizing the marginal likelihood of the observed labels. Our model achieves substantially boosts the performance of graph neural networks, and the learned parameters can also be interpreted as the strength of correlation among connected vertices. To allow us to scale to large networks, we design linear time algorithms for low-variance, unbiased model parameter estimates based on stochastic trace estimation. We also provide a simplified version of our method that makes stronger assumptions on correlation structure but is extremely easy to implement and provides great practical performance in several cases.

Partial-label learning is one of the important weakly supervised learning problems, where each training example is equipped with a set of candidate labels that contains the true label. Most existing methods elaborately designed learning objectives as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. The goal of this paper is to propose a novel framework of partial-label learning without implicit assumptions on the model or optimization algorithm. More specifically, we propose a general estimator of the classification risk, theoretically analyze the classifier-consistency, and establish an estimation error bound. We then explore a progressive identification method for approximately minimizing the proposed risk estimator, where the update of the model and identification of true labels are conducted in a seamless manner. The resulting algorithm is model-independent and loss-independent, and compatible with stochastic optimization. Thorough experiments demonstrate it sets the new state of the art.

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself. These approaches have shown good performance gain, especially in complicated dialogue domains with dynamic slot values. However, they fall short in two aspects: (1) they do not allow models to explicitly learn signals across domains and slots to detect potential dependencies among (domain, slot) pairs; and (2) existing models follow auto-regressive approaches which incur high time cost when the dialogue evolves over multiple domains and multiple turns. In this paper, we propose a novel framework of Non-Autoregressive Dialog State Tracking (NADST) which can factor in potential dependencies among domains and slots to optimize the models towards better prediction of dialogue states as a complete set rather than separate slots. In particular, the non-autoregressive nature of our method not only enables decoding in parallel to significantly reduce the latency of DST for real-time dialogue response generation, but also detect dependencies among slots at token level in addition to slot and domain level. Our empirical results show that our model achieves the state-of-the-art joint accuracy across all domains on the MultiWOZ 2.1 corpus, and the latency of our model is an order of magnitude lower than the previous state of the art as the dialogue history extends over time.

Do you know why I got into SEO? Not many people know this, but I grew up in middle-class America, and I wanted a better life for me and my parents. When I was 16 years old, I worked at a theme park called Knotts Berry Farm where I picked up trash, cleaned restrooms, and swept up vomit every single day. I didn't mind it because that's life and I needed the money. At 16, I realized I was too young to get a high paying job, so I did the next best thing… I started a business.

IESE Business School has launched a new Artificial Intelligence and the Future of Management Initiative, a multidisciplinary project that will look at how artificial intelligence is impacting management, and prepare executives to put Al to use in their companies in an ethical and socially responsible way. Artificial intelligence, like electricity a century ago, is a general purpose technology that will touch every sphere of economic activity. That places new demands on managers to adapt to the changing competitive landscape, to transform their organizations, and to ensure that employees – and themselves -- have the skills required. IESE's new Artificial Intelligence and the Future of Management Initiative will meet those needs for research and education efforts by: "AI is as much a management challenge as it is a technological challenge," said Dean Franz Heukamp. "With this initiative we want to help current and future managers, as well as policy makers, face the challenges AI presents, enabling them to shape the ways AI is used and ensure that it's a force for good in society."