Yunfeng Zhang

Priyam Basu, Yunfeng Zhang, Vipul Raheja · deepmind

AI-generated text detectors have recently gained adoption in educational and professional contexts. Prior research has uncovered isolated cases of bias, particularly against English Language Learners (ELLs) however, there is a lack of systematic evaluation of such systems across broader sociolinguistic factors. In this work, we propose BAID, a comprehensive evaluation framework for AI detectors across various types of biases. As a part of the framework, we introduce over 200k samples spanning 7 major categories: demographics, age, educational grade level, dialect, formality, political leaning, and topic. We also generated synthetic versions of each sample with carefully crafted prompts to preserve the original content while reflecting subgroup-specific writing styles. Using this, we evaluate four open-source state-of-the-art AI text detectors and find consistent disparities in detection performance, particularly low recall rates for texts from underrepresented groups. Our contributions provide a scalable, transparent approach for auditing AI detectors and emphasize the need for bias-aware evaluation before these tools are deployed for public use.

Q. Vera Liao, Yunfeng Zhang, Ronny Luss et al.

Recent years have seen a surge of interest in the field of explainable AI (XAI), with a plethora of algorithms proposed in the literature. However, a lack of consensus on how to evaluate XAI hinders the advancement of the field. We highlight that XAI is not a monolithic set of technologies -- researchers and practitioners have begun to leverage XAI algorithms to build XAI systems that serve different usage contexts, such as model debugging and decision-support. Algorithmic research of XAI, however, often does not account for these diverse downstream usage contexts, resulting in limited effectiveness or even unintended consequences for actual users, as well as difficulties for practitioners to make technical choices. We argue that one way to close the gap is to develop evaluation methods that account for different user requirements in these usage contexts. Towards this goal, we introduce a perspective of contextualized XAI evaluation by considering the relative importance of XAI evaluation criteria for prototypical usage contexts of XAI. To explore the context dependency of XAI evaluation criteria, we conduct two survey studies, one with XAI topical experts and another with crowd workers. Our results urge for responsible AI research with usage-informed evaluation practices, and provide a nuanced understanding of user requirements for XAI in different usage contexts.

Vivian Lai, Samuel Carton, Rajat Bhatnagar et al.

Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples. It remains an open question how such imperfect models can be used effectively in collaboration with humans. Prior work has focused on AI assistance that helps people make individual high-stakes decisions, which is not scalable for a large amount of relatively low-stakes decisions, e.g., moderating social media comments. Instead, we propose conditional delegation as an alternative paradigm for human-AI collaboration where humans create rules to indicate trustworthy regions of a model. Using content moderation as a testbed, we develop novel interfaces to assist humans in creating conditional delegation rules and conduct a randomized experiment with two datasets to simulate in-distribution and out-of-distribution scenarios. Our study demonstrates the promise of conditional delegation in improving model performance and provides insights into design for this novel paradigm, including the effect of AI explanations.

Kristian Lum, Yunfeng Zhang, Amanda Bower

When a model's performance differs across socially or culturally relevant groups--like race, gender, or the intersections of many such groups--it is often called "biased." While much of the work in algorithmic fairness over the last several years has focused on developing various definitions of model fairness (the absence of group-wise model performance disparities) and eliminating such "bias," much less work has gone into rigorously measuring it. In practice, it important to have high quality, human digestible measures of model performance disparities and associated uncertainty quantification about them that can serve as inputs into multi-faceted decision-making processes. In this paper, we show both mathematically and through simulation that many of the metrics used to measure group-wise model performance disparities are themselves statistically biased estimators of the underlying quantities they purport to represent. We argue that this can cause misleading conclusions about the relative group-wise model performance disparities along different dimensions, especially in cases where some sensitive variables consist of categories with few members. We propose the "double-corrected" variance estimator, which provides unbiased estimates and uncertainty quantification of the variance of model performance across groups. It is conceptually simple and easily implementable without statistical software package or numerical optimization. We demonstrate the utility of this approach through simulation and show on a real dataset that while statistically biased estimators of group-wise model performance disparities indicate statistically significant differences, when accounting for statistical bias in the estimator, the estimated between-group disparities are no longer statistically significant.

Wei Zhang, Junjie Tong, Fang Liao et al.

Accurate diagnosis of propeller faults is crucial for ensuring the safe and efficient operation of quadrotors. Training a fault classifier using simulated data and deploying it on a real quadrotor is a cost-effective and safe approach. However, the simulation-to-reality gap often leads to poor performance of the classifier when applied in real flight. In this work, we propose a deep learning model that addresses this issue by utilizing newly identified features (NIF) as input and utilizing domain adaptation techniques to reduce the simulation-to-reality gap. In addition, we introduce an adjusted simulation model that generates training data that more accurately reflects the behavior of real quadrotors. The experimental results demonstrate that our proposed approach achieves an accuracy of 96\% in detecting propeller faults. To the best of our knowledge, this is the first reliable and efficient method for simulation-to-reality fault diagnosis of quadrotor propellers.

Weilong Guo, Yuchen Wang, Renping Zhou et al.

Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps language instructions and visual observations to actions in a single forward pass. While conceptually simple, this formulation entangles instruction comprehension, spatial scene understanding, and motor control within a single learning objective. As a result, the action expert must implicitly relearn cognitive and perceptual capabilities already present in the pretrained VLM, which can limit both learning efficiency and generalization. We introduce AVP (Action with Visual Primitives), an end-to-end architecture that implements this visual-primitive-centric interface: the VLM infers the next-stage target and emits visual-primitive tokens that condition a flow-matching action expert, with supervision derived from end-effector kinematics. Real-robot experiments on general pick-and-place tasks show that AVP improves the success rate by 27.61% over pi_0.5 and outperforms other recent methods, with consistent gains in data efficiency, spatial-compositional generalization, and object-level transfer.

Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen et al.

As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, have different explanation needs. To address these needs, in 2019, we created AI Explainability 360 (Arya et al. 2020), an open source software toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. This paper examines the impact of the toolkit with several case studies, statistics, and community feedback. The different ways in which users have experienced AI Explainability 360 have resulted in multiple types of impact and improvements in multiple metrics, highlighted by the adoption of the toolkit by the independent LF AI & Data Foundation. The paper also describes the flexible design of the toolkit, examples of its use, and the significant educational material and documentation available to its users.

Soumya Ghosh, Q. Vera Liao, Karthikeyan Natesan Ramamurthy et al.

In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models. The goal of this toolkit is twofold: first, to provide a broad range of capabilities to streamline as well as foster the common practices of quantifying, evaluating, improving, and communicating uncertainty in the AI application development lifecycle; second, to encourage further exploration of UQ's connections to other pillars of trustworthy AI such as fairness and transparency through the dissemination of latest research and education materials. Beyond the Python package (\url{https://github.com/IBM/UQ360}), we have developed an interactive experience (\url{http://uq360.mybluemix.net}) and guidance materials as educational tools to aid researchers and developers in producing and communicating high-quality uncertainties in an effective manner.

Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen et al.

As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, present different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360 (http://aix360.mybluemix.net/), an open-source software toolkit featuring eight diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. We also discuss enhancements to bring research innovations closer to consumers of explanations, ranging from simplified, more accessible versions of algorithms, to tutorials and an interactive web demo to introduce AI explainability to different audiences and application domains. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.

Rachel K. E. Bellamy, Kuntal Dey, Michael Hind et al.

Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license {https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience (https://aif360.mybluemix.net) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.

Difei Cheng, Yunfeng Zhang, Ruinan Jin

K-medoids clustering is a popular variant of k-means clustering and widely used in pattern recognition and machine learning. A main drawback of k-medoids clustering is that an improper initialization can cause it to get trapped in local optima. An improved k-medoids clustering algorithm, called INCKM algorithm, which is the first to apply incremental initialization to k-medoids clustering, was recently proposed to overcome this drawback. The INCKM algorithm requires the construction of a subset of candidate medoids determined by one hyperparameter for initialization, and meanwhile, it always fails when dealing with imbalanced datasets with an incorrect hyperparameter selection. In this paper, we propose a novel k-medoids clustering algorithm, called incremental k-means++ (INCKPP) algorithm, which initializes with a novel incremental manner, attempting to optimally add one new cluster center at each stage through a nonparametric and stochastic k-means++ initialization. The INCKPP algorithm overcomes the difficulty of hyperparameter selection in the INCKM algorithm, improves the clustering performance, and can deal with imbalanced datasets well. However, the INCKPP algorithm is not computationally efficient enough. To deal with this, we further propose an improved INCKPP algorithm, called INCKPPsample algorithm, which improves the clustering efficiency while maintaining the clustering performance of the INCKPP algorithm. Extensive results from experiments on both synthetic and real-world datasets, including imbalanced datasets, illustrate that the proposed algorithms outperforms than the other compared algorithms.

Edward Sun, Yufang Hou, Dakuo Wang et al.

Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming to automate the document-to-slides generation process and all face a critical challenge: no publicly available dataset for training and benchmarking. In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years' NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a two-step approach: 1) Use slide titles to retrieve relevant and engaging text, figures, and tables; 2) Summarize the retrieved context into bullet points with long-form question answering. Our evaluation suggests that long-form QA outperforms state-of-the-art summarization baselines on both automated ROUGE metrics and qualitative human evaluation.

Shweta Narkar, Yunfeng Zhang, Q. Vera Liao et al.

Automated Machine Learning (AutoML) is a rapidly growing set of technologies that automate the model development pipeline by searching model space and generating candidate models. A critical, final step of AutoML is human selection of a final model from dozens of candidates. In current AutoML systems, selection is supported only by performance metrics. Prior work has shown that in practice, people evaluate ML models based on additional criteria, such as the way a model makes predictions. Comparison may happen at multiple levels, from types of errors, to feature importance, to how the model makes predictions of specific instances. We developed \tool{} to support interactive model comparison for AutoML by integrating multiple Explainable AI (XAI) and visualization techniques. We conducted a user study in which we both evaluated the system and used it as a technology probe to understand how users perform model comparison in an AutoML system. We discuss design implications for utilizing XAI techniques for model comparison and supporting the unique needs of data scientists in comparing AutoML models.

Wei Zhang, Yunfeng Zhang, Ning Liu et al.

This paper studies how to improve the generalization performance and learning speed of the navigation agents trained with deep reinforcement learning (DRL). Although DRL exhibits huge potential in robot mapless navigation, DRL agents performing well in training scenarios are often found to perform poorly in unfamiliar scenarios. In this work, we propose that the representation of LiDAR readings is a key factor behind the degradation of agents' performance and present a powerful input pre-processing (IP) approach to address this issue. As this approach uses adaptively parametric reciprocal functions to pre-process LiDAR readings, we refer to this approach as IPAPRec and its normalized version as IPAPRecN. IPAPRec/IPAPRecN can highlight important short-distance values and compress the range of less-important long-distance values in laser scans, which well address the issues induced by conventional representations of laser scans. Their high performance was validated by extensive simulation and real-world experiments. The results show that our methods can substantially improve navigation agents' generalization performance and greatly reduce the training time compared to conventional methods.

Dakuo Wang, Q. Vera Liao, Yunfeng Zhang et al.

Data science and machine learning (DS/ML) are at the heart of the recent advancements of many Artificial Intelligence (AI) applications. There is an active research thread in AI, \autoai, that aims to develop systems for automating end-to-end the DS/ML Lifecycle. However, do DS and ML workers really want to automate their DS/ML workflow? To answer this question, we first synthesize a human-centered AutoML framework with 6 User Role/Personas, 10 Stages and 43 Sub-Tasks, 5 Levels of Automation, and 5 Types of Explanation, through reviewing research literature and marketing reports. Secondly, we use the framework to guide the design of an online survey study with 217 DS/ML workers who had varying degrees of experience, and different user roles "matching" to our 6 roles/personas. We found that different user personas participated in distinct stages of the lifecycle -- but not all stages. Their desired levels of automation and types of explanation for AutoML also varied significantly depending on the DS/ML stage and the user persona. Based on the survey results, we argue there is no rationale from user needs for complete automation of the end-to-end DS/ML lifecycle. We propose new next steps for user-controlled DS/ML automation.

Umang Bhatt, Javier Antorán, Yunfeng Zhang et al.

Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most research into algorithmic transparency has predominantly focused on explainability. Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders. However, understanding a model's specific behavior alone might not be enough for stakeholders to gauge whether the model is wrong or lacks sufficient knowledge to solve the task at hand. In this paper, we argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. First, we discuss methods for assessing uncertainty. Then, we characterize how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. Finally, we outline methods for displaying uncertainty to stakeholders and recommend how to collect information required for incorporating uncertainty into existing ML pipelines. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness. We aim to encourage researchers and practitioners to measure, communicate, and use uncertainty as a form of transparency.

Wei Zhang, Ning Liu, Yunfeng Zhang

Deep reinforcement learning (DRL) demonstrates great potential in mapless navigation domain. However, such a navigation model is normally restricted to a fixed configuration of the range sensor because its input format is fixed. In this paper, we propose a DRL model that can address range data obtained from different range sensors with different installation positions. Our model first extracts the goal-directed features from each obstacle point. Subsequently, it chooses global obstacle features from all point-feature candidates and uses these features for the final decision. As only a few points are used to support the final decision, we refer to these points as support points and our approach as support point-based navigation (SPN). Our model can handle data from different LiDAR setups and demonstrates good performance in simulation and real-world experiments. Moreover, it shows great potential in crowded scenarios with small obstacles when using a high-resolution LiDAR.

Charvi Rastogi, Yunfeng Zhang, Dennis Wei et al.

Several strands of research have aimed to bridge the gap between artificial intelligence (AI) and human decision-makers in AI-assisted decision-making, where humans are the consumers of AI model predictions and the ultimate decision-makers in high-stakes applications. However, people's perception and understanding are often distorted by their cognitive biases, such as confirmation bias, anchoring bias, availability bias, to name a few. In this work, we use knowledge from the field of cognitive science to account for cognitive biases in the human-AI collaborative decision-making setting, and mitigate their negative effects on collaborative performance. To this end, we mathematically model cognitive biases and provide a general framework through which researchers and practitioners can understand the interplay between cognitive biases and human-AI accuracy. We then focus specifically on anchoring bias, a bias commonly encountered in human-AI collaboration. We implement a time-based de-anchoring strategy and conduct our first user experiment that validates its effectiveness in human-AI collaborative decision-making. With this result, we design a time allocation strategy for a resource-constrained setting that achieves optimal human-AI collaboration under some assumptions. We, then, conduct a second user experiment which shows that our time allocation strategy with explanation can effectively de-anchor the human and improve collaborative performance when the AI model has low confidence and is incorrect.

Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang et al.

We propose a new active learning (AL) framework, Active Learning++, which can utilize an annotator's labels as well as its rationale. Annotators can provide their rationale for choosing a label by ranking input features based on their importance for a given query. To incorporate this additional input, we modified the disagreement measure for a bagging-based Query by Committee (QBC) sampling strategy. Instead of weighing all committee models equally to select the next instance, we assign higher weight to the committee model with higher agreement with the annotator's ranking. Specifically, we generated a feature importance-based local explanation for each committee model. The similarity score between feature rankings provided by the annotator and the local model explanation is used to assign a weight to each corresponding committee model. This approach is applicable to any kind of ML model using model-agnostic techniques to generate local explanation such as LIME. With a simulation study, we show that our framework significantly outperforms a QBC based vanilla AL framework.

Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang et al.

Social biases based on gender, race, etc. have been shown to pollute machine learning (ML) pipeline predominantly via biased training datasets. Crowdsourcing, a popular cost-effective measure to gather labeled training datasets, is not immune to the inherent social biases of crowd workers. To ensure such social biases aren't passed onto the curated datasets, it's important to know how biased each crowd worker is. In this work, we propose a new method based on counterfactual fairness to quantify the degree of inherent social bias in each crowd worker. This extra information can be leveraged together with individual worker responses to curate a less biased dataset.

Karthikeyan Natesan Ramamurthy, Bhanukiran Vinzamuri, Yunfeng Zhang et al.

In recent years, post-hoc local instance-level and global dataset-level explainability of black-box models has received a lot of attention. Much less attention has been given to obtaining insights at intermediate or group levels, which is a need outlined in recent works that study the challenges in realizing the guidelines in the General Data Protection Regulation (GDPR). In this paper, we propose a meta-method that, given a typical local explainability method, can build a multilevel explanation tree. The leaves of this tree correspond to the local explanations, the root corresponds to the global explanation, and intermediate levels correspond to explanations for groups of data points that it automatically clusters. The method can also leverage side information, where users can specify points for which they may want the explanations to be similar. We argue that such a multilevel structure can also be an effective form of communication, where one could obtain few explanations that characterize the entire dataset by considering an appropriate level in our explanation tree. Explanations for novel test points can be cost-efficiently obtained by associating them with the closest training points. When the local explainability technique is generalized additive (viz. LIME, GAMs), we develop a fast approximate algorithm for building the multilevel tree and study its convergence behavior. We validate the effectiveness of the proposed technique based on two human studies -- one with experts and the other with non-expert users -- on real world datasets, and show that we produce high fidelity sparse explanations on several other public datasets.

Wei Zhang, Yunfeng Zhang, Ning Liu et al.

Deep reinforcement learning (DRL) has exhibited considerable promise in the training of control agents for mapless robot navigation. However, DRL-trained agents are limited to the specific robot dimensions used during training, hindering their applicability when the robot's dimension changes for task-specific requirements. To overcome this limitation, we propose a dimension-variable robot navigation method based on DRL. Our approach involves training a meta agent in simulation and subsequently transferring the meta skill to a dimension-varied robot using a technique called dimension-variable skill transfer (DVST). During the training phase, the meta agent for the meta robot learns self-navigation skills with DRL. In the skill-transfer phase, observations from the dimension-varied robot are scaled and transferred to the meta agent, and the resulting control policy is scaled back to the dimension-varied robot. Through extensive simulated and real-world experiments, we demonstrated that the dimension-varied robots could successfully navigate in unknown and dynamic environments without any retraining. The results show that our work substantially expands the applicability of DRL-based navigation methods, enabling them to be used on robots with different dimensions without the limitation of a fixed dimension. The video of our experiments can be found in the supplementary file.

Yunfeng Zhang, Rachel K. E. Bellamy, Kush R. Varshney

Today, AI is increasingly being used in many high-stakes decision-making applications in which fairness is an important concern. Already, there are many examples of AI being biased and making questionable and unfair decisions. The AI research community has proposed many methods to measure and mitigate unwanted biases, but few of them involve inputs from human policy makers. We argue that because different fairness criteria sometimes cannot be simultaneously satisfied, and because achieving fairness often requires sacrificing other objectives such as model accuracy, it is key to acquire and adhere to human policy makers' preferences on how to make the tradeoff among these objectives. In this paper, we propose a framework and some exemplar methods for eliciting such preferences and for optimizing an AI model according to these preferences.

Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang et al.

The wide adoption of Machine Learning technologies has created a rapidly growing demand for people who can train ML models. Some advocated the term "machine teacher" to refer to the role of people who inject domain knowledge into ML models. One promising learning paradigm is Active Learning (AL), by which the model intelligently selects instances to query the machine teacher for labels. However, in current AL settings, the human-AI interface remains minimal and opaque. We begin considering AI explanations as a core element of the human-AI interface for teaching machines. When a human student learns, it is a common pattern to present one's own reasoning and solicit feedback from the teacher. When a ML model learns and still makes mistakes, the human teacher should be able to understand the reasoning underlying the mistakes. When the model matures, the machine teacher should be able to recognize its progress in order to trust and feel confident about their teaching outcome. Toward this vision, we propose a novel paradigm of explainable active learning (XAL), by introducing techniques from the recently surging field of explainable AI (XAI) into an AL setting. We conducted an empirical study comparing the model learning outcomes, feedback content and experience with XAL, to that of traditional AL and coactive learning (providing the model's prediction without the explanation). Our study shows benefits of AI explanation as interfaces for machine teaching--supporting trust calibration and enabling rich forms of teaching feedback, and potential drawbacks--anchoring effect with the model judgment and cognitive workload. Our study also reveals important individual factors that mediate a machine teacher's reception to AI explanations, including task knowledge, AI experience and need for cognition. By reflecting on the results, we suggest future directions and design implications for XAL.

Michael Hind, Dennis Wei, Yunfeng Zhang

Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be provided in training data, along with target labels. Using semi-synthetic data from credit approval and employee retention applications, experiments are conducted to investigate some practical considerations with TED, including its performance with different classification algorithms, varying numbers of explanations, and variability in explanations. A new algorithm is proposed to handle the case where some training examples do not have explanations. Our results show that TED is robust to increasing numbers of explanations, noisy explanations, and large fractions of missing explanations, thus making advances toward its practical deployment.

Yunfeng Zhang, Q. Vera Liao, Rachel K. E. Bellamy

Today, AI is being increasingly used to help human experts make decisions in high-stakes scenarios. In these scenarios, full automation is often undesirable, not only due to the significance of the outcome, but also because human experts can draw on their domain knowledge complementary to the model's to ensure task success. We refer to these scenarios as AI-assisted decision making, where the individual strengths of the human and the AI come together to optimize the joint decision outcome. A key to their success is to appropriately \textit{calibrate} human trust in the AI on a case-by-case basis; knowing when to trust or distrust the AI allows the human expert to appropriately apply their knowledge, improving decision outcomes in cases where the model is likely to perform poorly. This research conducts a case study of AI-assisted decision making in which humans and AI have comparable performance alone, and explores whether features that reveal case-specific model information can calibrate trust and improve the joint performance of the human and AI. Specifically, we study the effect of showing confidence score and local explanation for a particular prediction. Through two human experiments, we show that confidence score can help calibrate people's trust in an AI model, but trust calibration alone is not sufficient to improve AI-assisted decision making, which may also depend on whether the human can bring in enough unique knowledge to complement the AI's errors. We also highlight the problems in using local explanation for AI-assisted decision making scenarios and invite the research community to explore new approaches to explainability for calibrating human trust in AI.

Ronny Luss, Pin-Yu Chen, Amit Dhurandhar et al.

As the application of deep neural networks proliferates in numerous areas such as medical imaging, video surveillance, and self driving cars, the need for explaining the decisions of these models has become a hot research topic, both at the global and local level. Locally, most explanation methods have focused on identifying relevance of features, limiting the types of explanations possible. In this paper, we investigate a new direction by leveraging latent features to generate contrastive explanations; predictions are explained not only by highlighting aspects that are in themselves sufficient to justify the classification, but also by new aspects which if added will change the classification. The key contribution of this paper lies in how we add features to rich data in a formal yet humanly interpretable way that leads to meaningful results. Our new definition of "addition" uses latent features to move beyond the limitations of previous explanations and resolve an open question laid out in Dhurandhar, et. al. (2018), which creates local contrastive explanations but is limited to simple datasets such as grayscale images. The strength of our approach in creating intuitive explanations that are also quantitatively superior to other methods is demonstrated on three diverse image datasets (skin lesions, faces, and fashion apparel). A user study with 200 participants further exemplifies the benefits of contrastive information, which can be viewed as complementary to other state-of-the-art interpretability methods.

Jonathan Dodge, Q. Vera Liao, Yunfeng Zhang et al.

Ensuring fairness of machine learning systems is a human-in-the-loop process. It relies on developers, users, and the general public to identify fairness problems and make improvements. To facilitate the process we need effective, unbiased, and user-friendly explanations that people can confidently rely on. Towards that end, we conducted an empirical study with four types of programmatically generated explanations to understand how they impact people's fairness judgments of ML systems. With an experiment involving more than 160 Mechanical Turk workers, we show that: 1) Certain explanations are considered inherently less fair, while others can enhance people's confidence in the fairness of the algorithm; 2) Different fairness problems--such as model-wide fairness issues versus case-specific fairness discrepancies--may be more effectively exposed through different styles of explanation; 3) Individual differences, including prior positions and judgment criteria of algorithmic fairness, impact how people react to different styles of explanation. We conclude with a discussion on providing personalized and adaptive explanations to support fairness judgments of ML systems.

Neil Mallinar, Abhishek Shah, Rajendra Ugrani et al.

Many conversational agents in the market today follow a standard bot development framework which requires training intent classifiers to recognize user input. The need to create a proper set of training examples is often the bottleneck in the development process. In many occasions agent developers have access to historical chat logs that can provide a good quantity as well as coverage of training examples. However, the cost of labeling them with tens to hundreds of intents often prohibits taking full advantage of these chat logs. In this paper, we present a framework called \textit{search, label, and propagate} (SLP) for bootstrapping intents from existing chat logs using weak supervision. The framework reduces hours to days of labeling effort down to minutes of work by using a search engine to find examples, then relies on a data programming approach to automatically expand the labels. We report on a user study that shows positive user feedback for this new approach to build conversational agents, and demonstrates the effectiveness of using data programming for auto-labeling. While the system is developed for training conversational agents, the framework has broader application in significantly reducing labeling effort for training text classifiers.

Yunfeng Zhang, Irina Gaynanova

Multi-view data, that is matched sets of measurements on the same subjects, have become increasingly common with advances in multi-omics technology. Often, it is of interest to find associations between the views that are related to the intrinsic class memberships. Existing association methods cannot directly incorporate class information, while existing classification methods do not take into account between-views associations. In this work, we propose a framework for Joint Association and Classification Analysis of multi-view data (JACA). Our goal is not to merely improve the misclassification rates, but to provide a latent representation of high-dimensional data that is both relevant for the subtype discrimination and coherent across the views. We motivate the methodology by establishing a connection between canonical correlation analysis and discriminant analysis. We also establish the estimation consistency of JACA in high-dimensional settings. A distinct advantage of JACA is that it can be applied to the multi-view data with block-missing structure, that is to cases where a subset of views or class labels is missing for some subjects. The application of JACA to quantify the associations between RNAseq and miRNA views with respect to consensus molecular subtypes in colorectal cancer data from The Cancer Genome Atlas project leads to improved misclassification rates and stronger found associations compared to existing methods.

Wei Zhang, Yunfeng Zhang, Ning Liu

Self-navigation, referred as the capability of automatically reaching the goal while avoiding collisions with obstacles, is a fundamental skill required for mobile robots. Recently, deep reinforcement learning (DRL) has shown great potential in the development of robot navigation algorithms. However, it is still difficult to train the robot to learn goal-reaching and obstacle-avoidance skills simultaneously. On the other hand, although many DRL-based obstacle-avoidance algorithms are proposed, few of them are reused for more complex navigation tasks. In this paper, a novel danger-aware adaptive composition (DAAC) framework is proposed to combine two individually DRL-trained agents, obstacle-avoidance and goal-reaching, to construct a navigation agent without any redesigning and retraining. The key to this adaptive composition approach is that the value function outputted by the obstacle-avoidance agent serves as an indicator for evaluating the risk level of the current situation, which in turn determines the contribution of these two agents for the next move. Simulation and real-world testing results show that the composed Navigation network can control the robot to accomplish difficult navigation tasks, e.g., reaching a series of successive goals in an unknown and complex environment safely and quickly.

Yunfeng Zhang

Traditional relative pointing devices such as mice and trackpads are unsuitable for pointing at distant displays, because they encumber the users by requiring either a flat surface to operate on or being held by two hands. Past research has examined many new pointing methods, but few could surpass the speed and accuracy of mice and trackpads. This paper introduces a new pointing system that is developed based on HTC Vive, a relatively low-cost virtual reality system, and proposes two methods of combining absolute and relative pointing. The proposed methods were compared against single-mode pointing methods (i.e., pure absolute pointing and pure relative pointing) in a Fitts' law study. The results show that with only a short period of practice, one hybrid pointing technique enabled faster and more accurate pointing than both single-mode pointing techniques, which included a trackpad.

Yedendra B. Shrinivasan, Yunfeng Zhang

Developing applications for interactive space is different from developing cross-platform applications for personal computing. Input, output, and architectural variations in each interactive space introduce big overhead in terms of cost and time for developing, deploying and maintaining applications for interactive spaces. Often, these applications become on-off experience tied to the deployed spaces. To alleviate this problem and enable rapid responsive space design applications similar to responsive web design, we present CELIO application development framework for interactive spaces. The framework is micro services based and neatly decouples application and design specifications from hardware and architecture specifications of an interactive space. In this paper, we describe this framework and its implementation details. Also, we briefly discuss the use cases developed using this framework.