With the rapid growth of cloud computing, a variety of software services have been deployed in the cloud. To ensure the reliability of cloud services, prior studies focus on failure instance (disk, node, and switch, etc.) prediction. Once the output of prediction is positive, mitigation actions are taken to rapidly resolve the underlying failure. According to our real-world practice in Microsoft Azure, we find that the prediction accuracy may decrease by about 9% after retraining the models. Considering that the mitigation actions may result in uncertain positive instances since they cannot be verified after mitigation, which may introduce more noise while updating the prediction model. To the best of our knowledge, we are the first to identify this Uncertain Positive Learning (UPLearning) issue in the real-world cloud failure prediction scenario. To tackle this problem, we design an Uncertain Positive Learning Risk Estimator (Uptake) approach. Using two real-world datasets of disk failure prediction and conducting node prediction experiments in Microsoft Azure, which is a top-tier cloud provider that serves millions of users, we demonstrate Uptake can significantly improve the failure prediction accuracy by 5% on average.

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the \texttt{Shifts Challenge on Robustness and Uncertainty under Real-World Distributional Shift} challenge. We find that by leveraging a mixture of experts in conjunction with an advanced data augmentation technique borrowed from the computer vision domain, in conjunction with robust \textit{post-hoc} calibration of predictive uncertainties, we can potentially achieve more accurate and better-calibrated results with deep neural networks than with boosted tree models for tabular data. We quantify our predictions using several metrics and propose several future lines of inquiry and experimentation to boost performance.

We employ an agent-based contact network model to study the relationship between vaccine uptake and disease dynamics in a hypothetical country town from New South Wales, Australia, undergoing a COVID-19 epidemic, over a period of three years. We model the contact network in this hypothetical township of N = 10000 people as a scale-free network, and simulate the spread of COVID-19 and vaccination program using disease and vaccination uptake parameters typically observed in such a NSW town. We simulate the spread of the ancestral variant of COVID-19 in this town, and study the disease dynamics while the town maintains limited but non-negligible contact with the rest of the country which is assumed to be undergoing a severe COVID-19 epidemic. We also simulate a maximum three doses of Pfizer Comirnaty vaccine being administered in this town, with limited vaccine supply at first which gradually increases, and analyse how the vaccination uptake affects the disease dynamics in this town, which is captured using an extended compartmental model with epidemic parameters typical for a COVID-19 epidemic in Australia. Our results show that, in such a township, three vaccination doses are sufficient to contain but not eradicate COVID-19, and the disease essentially becomes endemic. We also show that the average degree of infected nodes (the average number of contacts for infected people) predicts the proportion of infected people. Therefore, if the hubs (people with a relatively high number of contacts) are disproportionately infected, this indicates an oncoming peak of the infection, though the lag time thereof depends on the maximum number of vaccines administered to the populace. Overall, our analysis provides interesting insights in understanding the interplay between network topology, vaccination levels, and COVID-19 disease dynamics in a typical remote NSW country town.

Heterogeneous graph few-shot learning (HGFL) has been developed to address the label sparsity issue in heterogeneous graphs (HGs), which consist of various types of nodes and edges. The core concept of HGFL is to extract knowledge from rich-labeled classes in a source HG, transfer this knowledge to a target HG to facilitate learning new classes with few-labeled training data, and finally make predictions on unlabeled testing data. Existing methods typically assume that the source HG, training data, and testing data all share the same distribution. However, in practice, distribution shifts among these three types of data are inevitable due to two reasons: (1) the limited availability of the source HG that matches the target HG distribution, and (2) the unpredictable data generation mechanism of the target HG. Such distribution shifts result in ineffective knowledge transfer and poor learning performance in existing methods, thereby leading to a novel problem of out-of-distribution (OOD) generalization in HGFL. To address this challenging problem, we propose a novel Causal OOD Heterogeneous graph Few-shot learning model, namely COHF. In COHF, we first characterize distribution shifts in HGs with a structural causal model, establishing an invariance principle for OOD generalization in HGFL. Then, following this invariance principle, we propose a new variational autoencoder-based heterogeneous graph neural network to mitigate the impact of distribution shifts. Finally, by integrating this network with a novel meta-learning framework, COHF effectively transfers knowledge to the target HG to predict new classes with few-labeled data. Extensive experiments on seven real-world datasets have demonstrated the superior performance of COHF over the state-of-the-art methods.

Question answering (QA) is the task of answering questions posed in natural language with free-form natural language answers extracted from a given passage. In the OpenQA variant, only a question text is given, and the system must retrieve relevant passages from an unstructured knowledge source and use them to provide answers, which is the case in the mainstream QA systems on the Web. QA systems currently are mostly limited to the English language due to the lack of large-scale labeled QA datasets in non-English languages. In this paper, we show that effective, low-cost OpenQA systems can be developed for low-resource languages. The key ingredients are (1) weak supervision using machine-translated labeled datasets and (2) a relevant unstructured knowledge source in the target language. Furthermore, we show that only a few hundred gold assessment examples are needed to reliably evaluate these systems. We apply our method to Turkish as a challenging case study, since English and Turkish are typologically very distinct. We present SQuAD-TR, a machine translation of SQuAD2.0, and we build our OpenQA system by adapting ColBERT-QA for Turkish. We obtain a performance improvement of 9-34% in the EM score and 13-33% in the F1 score compared to the BM25-based and DPR-based baseline QA reader models by using two versions of Wikipedia dumps spanning two years. Our results show that SQuAD-TR makes OpenQA feasible for Turkish, which we hope encourages researchers to build OpenQA systems in other low-resource languages. We make all the code, models, and the dataset publicly available.

As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively evaluate algorithms that tackle the ``open-world''. To this end, we introduce NovelGym, a flexible and adaptable ecosystem designed to simulate gridworld environments, serving as a robust platform for benchmarking reinforcement learning (RL) and hybrid planning and learning agents in open-world contexts. The modular architecture of NovelGym facilitates rapid creation and modification of task environments, including multi-agent scenarios, with multiple environment transformations, thus providing a dynamic testbed for researchers to develop open-world AI agents.

As the use of Blockchain for digital payments continues to rise in popularity, it also becomes susceptible to various malicious attacks. Successfully detecting anomalies within Blockchain transactions is essential for bolstering trust in digital payments. However, the task of anomaly detection in Blockchain transaction data is challenging due to the infrequent occurrence of illicit transactions. Although several studies have been conducted in the field, a limitation persists: the lack of explanations for the model's predictions. This study seeks to overcome this limitation by integrating eXplainable Artificial Intelligence (XAI) techniques and anomaly rules into tree-based ensemble classifiers for detecting anomalous Bitcoin transactions. The Shapley Additive exPlanation (SHAP) method is employed to measure the contribution of each feature, and it is compatible with ensemble models. Moreover, we present rules for interpreting whether a Bitcoin transaction is anomalous or not. Additionally, we have introduced an under-sampling algorithm named XGBCLUS, designed to balance anomalous and non-anomalous transaction data. This algorithm is compared against other commonly used under-sampling and over-sampling techniques. Finally, the outcomes of various tree-based single classifiers are compared with those of stacking and voting ensemble classifiers. Our experimental results demonstrate that: (i) XGBCLUS enhances TPR and ROC-AUC scores compared to state-of-the-art under-sampling and over-sampling techniques, and (ii) our proposed ensemble classifiers outperform traditional single tree-based machine learning classifiers in terms of accuracy, TPR, and FPR scores.

We introduce context-aware translation, a novel method that combines the benefits of inpainting and image-to-image translation, respecting simultaneously the original input and contextual relevance -- where existing methods fall short. By doing so, our method opens new avenues for the controllable use of AI within artistic creation, from animation to digital art. As an use case, we apply our method to redraw any hand-drawn animated character eyes based on any design specifications - eyes serve as a focal point that captures viewer attention and conveys a range of emotions, however, the labor-intensive nature of traditional animation often leads to compromises in the complexity and consistency of eye design. Furthermore, we remove the need for production data for training and introduce a new character recognition method that surpasses existing work by not requiring fine-tuning to specific productions. This proposed use case could help maintain consistency throughout production and unlock bolder and more detailed design choices without the production cost drawbacks. A user study shows context-aware translation is preferred over existing work 95.16% of the time.

Governments are increasingly considering integrating autonomous AI agents in high-stakes military and foreign-policy decision-making, especially with the emergence of advanced generative AI models like GPT-4. Our work aims to scrutinize the behavior of multiple AI agents in simulated wargames, specifically focusing on their predilection to take escalatory actions that may exacerbate multilateral conflicts. Drawing on political science and international relations literature about escalation dynamics, we design a novel wargame simulation and scoring framework to assess the escalation risks of actions taken by these agents in different scenarios. Contrary to prior studies, our research provides both qualitative and quantitative insights and focuses on large language models (LLMs). We find that all five studied off-the-shelf LLMs show forms of escalation and difficult-to-predict escalation patterns. We observe that models tend to develop arms-race dynamics, leading to greater conflict, and in rare cases, even to the deployment of nuclear weapons. Qualitatively, we also collect the models' reported reasonings for chosen actions and observe worrying justifications based on deterrence and first-strike tactics. Given the high stakes of military and foreign-policy contexts, we recommend further examination and cautious consideration before deploying autonomous language model agents for strategic military or diplomatic decision-making.

The RoboCup competition was started in 1997, and is known as the oldest RoboCup league. The RoboCup 2D Soccer Simulation League is a stochastic, partially observable soccer environment in which 24 autonomous agents play on two opposing teams. In this paper, we detail the main strategies and functionalities of CYRUS, the RoboCup 2021 2D Soccer Simulation League champions. The new functionalities presented and discussed in this work are (i) Multi Action Dribble, (ii) Pass Prediction and (iii) Marking Decision. The Multi Action Dribbling strategy enabled CYRUS to succeed more often and to be safer when dribbling actions were performed during a game. The Pass Prediction enhanced our gameplay by predicting our teammate's passing behavior, anticipating and making our agents collaborate better towards scoring goals. Finally, the Marking Decision addressed the multi-agent matching problem to improve CYRUS defensive strategy by finding an optimal solution to mark opponents' players.