Ai Magazine最新文献

This work introduces the design, development, and deployment of a virtual driving instructor (VDI) for enhanced driver education. The VDI provides personalized, real-time feedback to students in a driving simulator, addressing some of the limitations of traditional driver instruction. Employing a hybrid AI system, the VDI combines rule-based agents, learning-based agents, knowledge graphs, and Bayesian networks to assess and monitor student performance in a comprehensive manner. Implemented in multiple simulators at a driving school in Norway, the system aims to leverage AI and driving simulation to improve both the learning experience and the efficiency of instruction. Initial feedback from students has been largely positive, highlighting the effectiveness of this integration while also pointing to areas for further improvement. This marks a significant stride in infusing technology into driver education, offering a scalable and efficient approach to instruction.

In the realm of business automation, conversational assistants are emerging as the primary method for making automation software accessible to users in various business sectors. Access to automation primarily occurs through application programming interface (APIs) and robotic process automation (RPAs). To effectively convert APIs and RPAs into chatbots on a larger scale, it is crucial to establish an automated process for generating data and training models that can recognize user intentions, identify questions for conversational slot filling, and provide recommendations for subsequent actions. In this paper, we present a technique for enhancing and generating natural language conversational artifacts from API specifications using large language models (LLMs). The goal is to utilize LLMs in the “build” phase to assist humans in creating skills for digital assistants. As a result, the system does not need to rely on LLMs during conversations with business users, leading to efficient deployment. Along with enabling digital assistants, our system employs LLMs as proxies to simulate human interaction and automatically evaluate the digital assistant's performance. Experimental results highlight the effectiveness of our proposed approach. Our system is deployed in the IBM Watson Orchestrate product for general availability.

Graph-structured data, ranging from social networks to financial transaction networks, from citation networks to gene regulatory networks, have been widely used for modeling a myriad of real-world systems. As a prevailing model architecture to model graph-structured data, graph neural networks (GNNs) have drawn much attention in both academic and industrial communities in the past decades. Despite their success in different graph learning tasks, existing methods usually rely on learning from “big” data, requiring a large amount of labeled data for model training. However, it is common that real-world graphs are associated with “small” labeled data as data annotation and labeling on graphs is always time and resource-consuming. Therefore, it is imperative to investigate graph machine learning (graph ML) with low-cost human supervision for low-resource settings where limited or even no labeled data is available. This paper investigates a new research field—data-efficient graph learning, which aims to push forward the performance boundary of graph ML models with different kinds of low-cost supervision signals. Specifically, we outline the fundamental research problems, review the current progress, and discuss the future prospects of data-efficient graph learning, aiming to illuminate the path for subsequent research in this field.

Visual interpretation is extremely important in human geography as the primary technique for geographers to use photograph data in identifying, classifying, and quantifying geographic and topological objects or regions. However, it is also time-consuming and requires overwhelming manual effort from professional geographers. This paper describes our interdisciplinary team's efforts in integrating computer vision models with geographers' visual image interpretation process to reduce their workload in interpreting images. Focusing on the dune segmentation task, we proposed an approach called $��{\mathrm{DCV}}^2�I�$ featuring a deep dune segmentation model to identify dunes and label their ranges in an automated way. By developing a tool to connect our model with ArcGIS—one of the most popular workbenches for visual interpretation, geographers can further refine the automatically generated dune segmentation on images without learning any CV or deep learning techniques. Our approach thus realized a noninvasive change to geographers' visual interpretation routines, reducing their manual efforts while incurring minimal interruptions to their work routines and tools they are familiar with. Deployment with a leading Chinese geography research institution demonstrated the potential of $��{\mathrm{DCV}}^2�I�$ in supporting geographers in researching and solving drylands desertification.

In the field of finance, the underwriting process is an essential step in evaluating every loan application. During this stage, the borrowers' creditworthiness and ability to repay the loan are assessed to ultimately decide whether to approve the loan application. One of the core components of underwriting is credit scoring, in which the probability of default is estimated. As such, there has been significant progress in enhancing the predictive accuracy of credit scoring models through the use of machine learning, but there still exists a need to ultimately construct an approval rule that takes into consideration additional criteria beyond the score itself. This construction process is traditionally done manually to ensure that the approval rule remains interpretable to humans. In this paper, we outline an automated system for optimizing a rule-based system for approving loan applications, which has been deployed at Hyundai Capital Services (HCS). The main challenge lays in creating a high-quality rule base that is simultaneously simple enough to be interpretable by risk analysts as well as customers, since the approval decision should be easily understandable. We addressed this challenge through principled submodular optimization. The deployment of our system has led to a 14% annual growth in the volume of loan services at HCS, while maintaining the target bad rate, and has resulted in the approval of customers who might have otherwise been rejected.

The increasingly decentralized and private nature of data in our digital society has motivated the development of collaborative intelligent systems that enable knowledge aggregation among data owners. However, collaborative learning has only been investigated in simple settings. For example, clients are often assumed to train solution models de novo, disregarding all prior expertise. The learned model is typically represented in task-specific forms that are not generalizable to unseen, emerging scenarios. Finally, a universal model representation is enforced among collaborators, ignoring their local compute constraints or input representations. These limitations hampers the practicality of prior collaborative systems in learning scenarios with limited task data that demand constant knowledge adaptation and transfer across information silos, tasks, and learning models, as well as the utilization of prior solution expertise. Furthermore, prior collaborative learning frameworks are not sustainable on a macro scale where participants desire fairness allocation of benefits (e.g., access to the combined model) based on their costs of participation (e.g., overhead of model sharing and training synchronization, risk of information breaches, etc.). This necessitates a new perspective of collaborative learning where the server not only aggregates but also conducts valuation of the participant's contribution, and distribute aggregated information to individuals in commensurate to their contribution. To substantiate the above vision, we propose a new research agenda on developing effective and sustainable collaborative learning frameworks across heterogeneous systems, featuring three novel computational capabilities on knowledge organization: model expression, comprehension, and valuation.

With the development of machine learning algorithms and the increasing computational resources available, artificial intelligence has achieved great success in many application domains. However, the success of machine learning has also raised concerns about the fairness of the learned models. For instance, the learned models can perpetuate and even exacerbate the potential bias and discrimination in the training data. This issue has become a major obstacle to the deployment of machine learning systems in high-stakes domains, for example, criminal judgment, medical testing, online advertising, hiring process, and so forth. To mitigate the potential bias exhibited by machine learning models, fairness criteria can be integrated into the training process to ensure fair treatment across all demographics, but it often comes at the expense of model performance. Understanding such tradeoffs, therefore, is crucial to the design of optimal and fair algorithms. My research focuses on characterizing the inherent tradeoff between fairness and accuracy in machine learning, and developing algorithms that can achieve both fairness and optimality. In this article, I will discuss our recent work on designing post-processing algorithms for fair classification, which can be applied to a wide range of fairness criteria, including statistical parity, equal opportunity, and equalized odds, under both attribute-aware and attribute-blind settings, and is particularly suited to large-scale foundation models where retraining is expensive or even infeasible. I will also discuss the connections between our work and other related research on trustworthy machine learning, including the connections between algorithmic fairness and differential privacy as well as adversarial robustness.

Sequential decision-making involves making informed decisions based on continuous interactions with a complex environment. This process is ubiquitous in various applications, including recommendation systems and clinical treatment design. My research has concentrated on addressing two pivotal challenges in sequential decision-making: (1) How can we design algorithms that efficiently learn the optimal decision strategy with minimal interactions and limited sample data? (2) How can we ensure robustness in decision-making algorithms when faced with distributional shifts due to environmental changes and the sim-to-real gap? This paper summarizes and expands upon the talk I presented at the AAAI 2024 New Faculty Highlights program, detailing how my research aims to tackle these challenges.

Understanding and correcting algorithmic bias in artificial intelligence (AI) has become increasingly important, leading to a surge in research on AI fairness within both the AI community and broader society. Traditionally, this research operates within the constrained supervised learning paradigm, assuming the presence of class labels, independent and identically distributed (IID) data, and batch-based learning necessitating the simultaneous availability of all training data. However, in practice, class labels may be absent due to censoring, data is often represented using non-IID graph structures that capture connections among individual units, and data can arrive and evolve over time. These prevalent real-world data representations limit the applicability of existing fairness literature, which typically addresses fairness in static and tabular supervised learning settings. This paper reviews recent advances in AI fairness aimed at bridging these gaps for practical deployment in real-world scenarios. Additionally, opportunities are envisioned by highlighting the limitations and significant potential for real applications.

Recently, there has been great interest in deploying autonomous mobile robots in airports, malls, and hospitals to complete a range of tasks such as delivery, cleaning, and patrolling. The rich context of these environments gives rise to highly unstructured motion that is challenging for robots to anticipate and adapt to. This results in uncomfortable and unsafe human–robot encounters, poor robot performance, and even catastrophic failures that hinder robot acceptance. Such observations have motivated my work on social robot navigation, the problem of enabling robots to navigate in human environments while accounting for human safety and comfort. In this article, I highlight prior work on expanding the classical autonomy stack with mathematical models and algorithms designed to contribute towards smoother mobile robot deployments in complex environments.