Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. To address this defect, state-of-the-art solutions choose to train deep networks on an auxiliary dataset of outliers. Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions. However, we find that these intuitively designed outlier training criteria can hurt in-distribution learning and eventually lead to inferior performance. To this end, we identify three causes of the in-distribution incompatibility: contradictory gradient, false likelihood, and distribution shift. Based on our new understandings, we propose a new out-of-distribution detection method by adapting both the top-design of deep models and the loss function. Our method achieves in-distribution compatibility by pursuing less interference with the probabilistic characteristic of in-distribution features. On several benchmarks, our method not only achieves the state-of-the-art out-of-distribution detection performance but also improves the in-distribution accuracy.

Debiasing word embeddings has been largely limited to individual and independent social categories. However, real-world corpora typically present multiple social categories that possibly correlate or intersect with each other. For instance, "hair weaves" is stereotypically associated with African American females, but neither African American nor females alone. Therefore, this work studies biases associated with multiple social categories: joint biases induced by the union of different categories and intersectional biases that do not overlap with the biases of the constituent categories. We first empirically observe that individual biases intersect non-trivially (i.e., over a one-dimensional subspace). Drawing from the intersectional theory in social science and the linguistic theory, we then construct an intersectional subspace to debias for multiple social categories using the nonlinear geometry of individual biases. Empirical evaluations corroborate the efficacy of our approach. Data and implementation code can be downloaded at https://github.com/GitHubLuCheng/Implementation-of-JoSEC-COLING-22.

Conflict-Based Search (CBS) is a popular multi-agent path finding (MAPF) solver that employs a low-level single agent planner and a high-level constraint tree to resolve conflicts. The vast majority of modern MAPF solvers focus on improving CBS by reducing the size of this tree through various strategies with few methods modifying the low level planner. Typically low level planners in existing CBS methods use an unweighted cost-to-go heuristic, with suboptimal CBS methods also using a conflict heuristic to help the high level search. In this paper, we show that, contrary to prevailing CBS beliefs, a weighted cost-to-go heuristic can be used effectively alongside the conflict heuristic in two possible variants. In particular, one of these variants can obtain large speedups, 2-100x, across several scenarios and suboptimal CBS methods. Importantly, we discover that performance is related not to the weighted cost-to-go heuristic but rather to the relative conflict heuristic weight's ability to effectively balance low-level and high-level work, implying that existing suboptimal CBS work misses this subtlety. Additionally, to the best of our knowledge, we show the first theoretical relation of prioritized planning and bounded suboptimal CBS and demonstrate that our methods are their natural generalization.

Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially relevant time-frequency bins in a spectrogram or time-pitch bins in a piano roll. This can be difficult to understand, particularly for musicologists without technical knowledge. To address this issue, we focus on more human-friendly explanations based on high-level musical concepts. Our research targets trained systems (post-hoc explanations) and explores two approaches: a supervised one, where the user can define a musical concept and test if it is relevant to the system; and an unsupervised one, where musical excerpts containing relevant concepts are automatically selected and given to the user for interpretation. We demonstrate both techniques on an existing symbolic composer classification system, showcase their potential, and highlight their intrinsic limitations.

Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural Networks (DNN). It offers many significant opportunities for improving DNN performance and efficiency and has been explored in a large body of work. These studies have scattered in many venues across several years. The targets they focus on range from images to videos and texts, and the techniques they use to detect and exploit data redundancy also vary in many aspects. There is not yet a systematic examination and summary of the many efforts, making it difficult for researchers to get a comprehensive view of the prior work, the state of the art, differences and shared principles, and the areas and directions yet to explore. This article tries to fill the void. It surveys hundreds of recent papers on the topic, introduces a novel taxonomy to put the various techniques into a single categorization framework, offers a comprehensive description of the main methods used for exploiting data redundancy in improving multiple kinds of DNNs on data, and points out a set of research opportunities for future to explore.

Customer Life Time Value (LTV) is the expected total revenue that a single user can bring to a business. It is widely used in a variety of business scenarios to make operational decisions when acquiring new customers. Modeling LTV is a challenging problem, due to its complex and mutable data distribution. Existing approaches either directly learn from posterior feature distributions or leverage statistical models that make strong assumption on prior distributions, both of which fail to capture those mutable distributions. In this paper, we propose a complete set of industrial-level LTV modeling solutions. Specifically, we introduce an Order Dependency Monotonic Network (ODMN) that models the ordered dependencies between LTVs of different time spans, which greatly improves model performance. We further introduce a Multi Distribution Multi Experts (MDME) module based on the Divide-and-Conquer idea, which transforms the severely imbalanced distribution modeling problem into a series of relatively balanced sub-distribution modeling problems hence greatly reduces the modeling complexity. In addition, a novel evaluation metric Mutual Gini is introduced to better measure the distribution difference between the estimated value and the ground-truth label based on the Lorenz Curve. The ODMN framework has been successfully deployed in many business scenarios of Kuaishou, and achieved great performance. Extensive experiments on real-world industrial data demonstrate the superiority of the proposed methods compared to state-of-the-art baselines including ZILN and Two-Stage XGBoost models.

Revolutions often have humble origins, a small group with big ideas gathering to plant seeds of disruption. So, it was in the dog days of summer in 1956, when 10 academics gathered on the campus of Dartmouth College to discuss how to make machines use language and form abstractions and concepts to solve the kinds of problems now reserved for humans. The conference led to the founding of a new field of study, artificial intelligence. Six decades hence, we are in the midst of an AI revolution that is already dramatically changing entire sectors like healthcare, transportation, education, banking, and retail. But AI is not without its critics. Elon Musk famously said that, "With artificial intelligence, we're summoning the demon." While Stephen Hawking believed the development of full artificial intelligence could spell the end of the human race. So, whose job is it to make sure that such a vision never comes to pass? Today on Cold Call, we've invited Professor Tsedal Neeley to discuss her case entitled, "Timnit Gebru: Silenced No More on AI Bias and The Harms of Large Language Models." Tsedal Neeley's work focuses on how leaders can scale their organizations by developing and implementing global and digital strategies.

The graph represents a network of 1,952 Twitter users whose tweets in the requested range contained "#FinServ", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Sunday, 28 August 2022 at 01:54 UTC. The requested start date was Sunday, 28 August 2022 at 00:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 7,500. The tweets in the network were tweeted over the 6-day, 11-hour, 15-minute period from Sunday, 21 August 2022 at 12:45 UTC to Sunday, 28 August 2022 at 00:00 UTC.

Finding solutions to improve turtle reidentification and supporting machine learning projects across Africa. Protecting the ecosystems around us is critical to safeguarding the future of our planet and all its living citizens. Fortunately, new artificial intelligence (AI) systems are making progress in conservation efforts worldwide, helping tackle complex problems at scale – from studying the behaviour of animal communities in the Serengeti to help conserve the diminishing ecosystem, to spotting poachers and their wounded prey to prevent species going extinct. As part of our mission to help benefit humanity with the technologies we develop, it's important we ensure diverse groups of people build the AI systems of the future so that it's equitable and fair. This includes broadening the machine learning (ML) community and engaging with wider audiences on addressing important problems using AI.

Madam Ama Pomaa Boateng, the Deputy Minister of Communication and Digitalisation, says Artificial Intelligence (AI) is now driving global digital revolution and solving problems and challenges for emerging economies. AI is the ability of a computer or a robot controlled by a computer to do tasks that are usually done by humans because they require human intelligence and discernment. Madam Boateng said this in Accra at the first face-to-face meet-up networking event on AI, organised by the Ghana-India Kofi Annan Centre of Excellence in ICT (GI-KACE). "Financial Inclusion using AI is a very good thing because it is part of the Sustainable Development Goals," she said. "It is actually seven out of the 17 goals that government and other institutions are working on by using AI to solve problems ….".