Bill Howe

Bingbing Wen, Jihan Yao, Shangbin Feng et al. · allen-ai, uw

Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in LLM systems. In this survey, we introduce a framework to examine abstention from three perspectives: the query, the model, and human values. We organize the literature on abstention methods, benchmarks, and evaluation metrics using this framework, and discuss merits and limitations of prior work. We further identify and motivate areas for future research, such as whether abstention can be achieved as a meta-capability that transcends specific tasks or domains, and opportunities to optimize abstention abilities in specific contexts. In doing so, we aim to broaden the scope and impact of abstention methodologies in AI systems.

Robert Wolfe, Yiwei Yang, Bill Howe et al.

Nine language-vision AI models trained on web scrapes with the Contrastive Language-Image Pretraining (CLIP) objective are evaluated for evidence of a bias studied by psychologists: the sexual objectification of girls and women, which occurs when a person's human characteristics, such as emotions, are disregarded and the person is treated as a body. We replicate three experiments in psychology quantifying sexual objectification and show that the phenomena persist in AI. A first experiment uses standardized images of women from the Sexual OBjectification and EMotion Database, and finds that human characteristics are disassociated from images of objectified women: the model's recognition of emotional state is mediated by whether the subject is fully or partially clothed. Embedding association tests (EATs) return significant effect sizes for both anger (d >0.80) and sadness (d >0.50), associating images of fully clothed subjects with emotions. GRAD-CAM saliency maps highlight that CLIP gets distracted from emotional expressions in objectified images. A second experiment measures the effect in a representative application: an automatic image captioner (Antarctic Captions) includes words denoting emotion less than 50% as often for images of partially clothed women than for images of fully clothed women. A third experiment finds that images of female professionals (scientists, doctors, executives) are likely to be associated with sexual descriptions relative to images of male professionals. A fourth experiment shows that a prompt of "a [age] year old girl" generates sexualized images (as determined by an NSFW classifier) up to 73% of the time for VQGAN-CLIP and Stable Diffusion; the corresponding rate for boys never surpasses 9%. The evidence indicates that language-vision AI models trained on web scrapes learn biases of sexual objectification, which propagate to downstream applications.

Yuxiang Zhang, Bill Howe, Sachin Mehta et al.

Applications to support pedestrian mobility in urban areas require a complete, and routable graph representation of the built environment. Globally available information, including aerial imagery provides a scalable source for constructing these path networks, but the associated learning problem is challenging: Relative to road network pathways, pedestrian network pathways are narrower, more frequently disconnected, often visually and materially variable in smaller areas, and their boundaries are broken up by driveway incursions, alleyways, marked or unmarked crossings through roadways. Existing algorithms to extract pedestrian pathway network graphs are inconsistently evaluated and tend to ignore routability, making it difficult to assess utility for mobility applications: Even if all path segments are available, discontinuities could dramatically and arbitrarily shift the overall path taken by a pedestrian. In this paper, we describe a first standard benchmark for the pedestrian pathway graph extraction problem, comprising the largest available dataset equipped with manually vetted ground truth annotations (covering $3,000 km^2$ land area in regions from 8 cities), and a family of evaluation metrics centering routability and downstream utility. By partitioning the data into polygons at the scale of individual intersections, we compute local routability as an efficient proxy for global routability. We consider multiple measures of polygon-level routability and compare predicted measures with ground truth to construct evaluation metrics. Using these metrics, we show that this benchmark can surface strengths and weaknesses of existing methods that are hidden by simple edge-counting metrics over single-region datasets used in prior work, representing a challenging, high-impact problem in computer vision and machine learning.

Bin Han, Yiwei Yang, Anat Caspi et al.

Equitable urban transportation applications require high-fidelity digital representations of the built environment: not just streets and sidewalks, but bike lanes, marked and unmarked crossings, curb ramps and cuts, obstructions, traffic signals, signage, street markings, potholes, and more. Direct inspections and manual annotations are prohibitively expensive at scale. Conventional machine learning methods require substantial annotated training data for adequate performance. In this paper, we consider vision language models as a mechanism for annotating diverse urban features from satellite images, reducing the dependence on human annotation to produce large training sets. While these models have achieved impressive results in describing common objects in images captured from a human perspective, their training sets are less likely to include strong signals for esoteric features in the built environment, and their performance in these settings is therefore unclear. We demonstrate proof-of-concept combining a state-of-the-art vision language model and variants of a prompting strategy that asks the model to consider segmented elements independently of the original image. Experiments on two urban features -- stop lines and raised tables -- show that while direct zero-shot prompting correctly annotates nearly zero images, the pre-segmentation strategies can annotate images with near 40% intersection-over-union accuracy. We describe how these results inform a new research agenda in automatic annotation of the built environment to improve equity, accessibility, and safety at broad scale and in diverse environments.

Robert Wolfe, Aayushi Dangol, Bill Howe et al.

Popular and news media often portray teenagers with sensationalism, as both a risk to society and at risk from society. As AI begins to absorb some of the epistemic functions of traditional media, we study how teenagers in two countries speaking two languages: 1) are depicted by AI, and 2) how they would prefer to be depicted. Specifically, we study the biases about teenagers learned by static word embeddings (SWEs) and generative language models (GLMs), comparing these with the perspectives of adolescents living in the U.S. and Nepal. We find English-language SWEs associate teenagers with societal problems, and more than 50% of the 1,000 words most associated with teenagers in the pretrained GloVe SWE reflect such problems. Given prompts about teenagers, 30% of outputs from GPT2-XL and 29% from LLaMA-2-7B GLMs discuss societal problems, most commonly violence, but also drug use, mental illness, and sexual taboo. Nepali models, while not free of such associations, are less dominated by social problems. Data from workshops with N=13 U.S. adolescents and N=18 Nepalese adolescents show that AI presentations are disconnected from teenage life, which revolves around activities like school and friendship. Participant ratings of how well 20 trait words describe teens are decorrelated from SWE associations, with Pearson's r=.02, n.s. in English FastText and r=.06, n.s. in GloVe; and r=.06, n.s. in Nepali FastText and r=-.23, n.s. in GloVe. U.S. participants suggested AI could fairly present teens by highlighting diversity, while Nepalese participants centered positivity. Participants were optimistic that, if it learned from adolescents, rather than media sources, AI could help mitigate stereotypes. Our work offers an understanding of the ways SWEs and GLMs misrepresent a developmentally vulnerable group and provides a template for less sensationalized characterization.

Robert Wolfe, Aayushi Dangol, Alexis Hiniker et al.

Multimodal AI models capable of associating images and text hold promise for numerous domains, ranging from automated image captioning to accessibility applications for blind and low-vision users. However, uncertainty about bias has in some cases limited their adoption and availability. In the present work, we study 43 CLIP vision-language models to determine whether they learn human-like facial impression biases, and we find evidence that such biases are reflected across three distinct CLIP model families. We show for the first time that the the degree to which a bias is shared across a society predicts the degree to which it is reflected in a CLIP model. Human-like impressions of visually unobservable attributes, like trustworthiness and sexuality, emerge only in models trained on the largest dataset, indicating that a better fit to uncurated cultural data results in the reproduction of increasingly subtle social biases. Moreover, we use a hierarchical clustering approach to show that dataset size predicts the extent to which the underlying structure of facial impression bias resembles that of facial impression bias in humans. Finally, we show that Stable Diffusion models employing CLIP as a text encoder learn facial impression biases, and that these biases intersect with racial biases in Stable Diffusion XL-Turbo. While pretrained CLIP models may prove useful for scientific studies of bias, they will also require significant dataset curation when intended for use as general-purpose models in a zero-shot setting.

Lucas Rosenblatt, Bin Han, Erin Posthumus et al.

An invasive species of grass known as "buffelgrass" contributes to severe wildfires and biodiversity loss in the Southwest United States. We tackle the problem of predicting buffelgrass "green-ups" (i.e. readiness for herbicidal treatment). To make our predictions, we explore temporal, visual and multi-modal models that combine satellite sensing and deep learning. We find that all of our neural-based approaches improve over conventional buffelgrass green-up models, and discuss how neural model deployment promises significant resource savings.

Bin Han, Bill Howe

We adapt image inpainting techniques to impute large, irregular missing regions in urban settings characterized by sparsity, variance in both space and time, and anomalous events. Missing regions in urban data can be caused by sensor or software failures, data quality issues, interference from weather events, incomplete data collection, or varying data use regulations; any missing data can render the entire dataset unusable for downstream applications. To ensure coverage and utility, we adapt computer vision techniques for image inpainting to operate on 3D histograms (2D space + 1D time) commonly used for data exchange in urban settings. Adapting these techniques to the spatiotemporal setting requires handling skew: urban data tend to follow population density patterns (small dense regions surrounded by large sparse areas); these patterns can dominate the learning process and fool the model into ignoring local or transient effects. To combat skew, we 1) train simultaneously in space and time, and 2) focus attention on dense regions by biasing the masks used for training to the skew in the data. We evaluate the core model and these two extensions using the NYC taxi data and the NYC bikeshare data, simulating different conditions for missing data. We show that the core model is effective qualitatively and quantitatively, and that biased masking during training reduces error in a variety of scenarios. We also articulate a tradeoff in varying the number of timesteps per training sample: too few timesteps and the model ignores transient events; too many timesteps and the model is slow to train with limited performance gain.

Bingbing Wen, Sirajul Salekin, Feiyang Kang et al.

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension, typically data format or task type. We introduce MixAtlas, a method that produces benchmark-targeted data recipes that can be inspected, adapted, and transferred to new corpora. MixAtlas decomposes the training corpus along two axes: image concepts (10 visual-domain clusters discovered via CLIP embeddings) and task supervision (5 objective types including captioning, OCR, grounding, detection, and VQA). Using small proxy models (Qwen2-0.5B) paired with a Gaussian-process surrogate and GP-UCB acquisition, MixAtlas searches the resulting mixture space with the same proxy budget as regression-based baselines but finds better-performing mixtures. We evaluate on 10 benchmarks spanning visual understanding, document reasoning, and multimodal reasoning. On Qwen2-7B, optimized mixtures improve average performance by 8.5%-17.6% over the strongest baseline; on Qwen2.5-7B, gains are 1.0%-3.3%. Both settings reach baseline-equivalent training loss in up to 2 times fewer steps. Recipes discovered on 0.5B proxies transfer to 7B-scale training across Qwen model families.

Bin Han, Bill Howe

Open data is frequently released spatially aggregated, usually to comply with privacy policies. But coarse, heterogeneous aggregations complicate learning and integration for downstream AI/ML systems. In this work, we consider models to disaggregate spatio-temporal data from a low-resolution, irregular partition (e.g., census tract) to a high-resolution, irregular partition (e.g., city block). We propose an overarching model named the Structurally-Aware Recurrent Network (SARN), which integrates structurally-aware spatial attention (SASA) layers into the Gated Recurrent Unit (GRU) model. The spatial attention layers capture spatial interactions among regions, while the gated recurrent module captures the temporal dependencies. Each SASA layer calculates both global and structural attention -- global attention facilitates comprehensive interactions between different geographic levels, while structural attention leverages the containment relationship between different geographic levels (e.g., a city block being wholly contained within a census tract) to ensure coherent and consistent results. For scenarios with limited historical training data, we explore transfer learning and show that a model pre-trained on one city variable can be fine-tuned for another city variable using only a few hundred samples. Evaluating these techniques on two mobility datasets, we find that on both datasets, SARN significantly outperforms other neural models (5% and 1%) and typical heuristic methods (40% and 14%), enabling us to generate realistic, high-quality fine-grained data for downstream applications.

Robert Wolfe, Alexis Hiniker, Bill Howe

This research introduces the Multilevel Embedding Association Test (ML-EAT), a method designed for interpretable and transparent measurement of intrinsic bias in language technologies. The ML-EAT addresses issues of ambiguity and difficulty in interpreting the traditional EAT measurement by quantifying bias at three levels of increasing granularity: the differential association between two target concepts with two attribute concepts; the individual effect size of each target concept with two attribute concepts; and the association between each individual target concept and each individual attribute concept. Using the ML-EAT, this research defines a taxonomy of EAT patterns describing the nine possible outcomes of an embedding association test, each of which is associated with a unique EAT-Map, a novel four-quadrant visualization for interpreting the ML-EAT. Empirical analysis of static and diachronic word embeddings, GPT-2 language models, and a CLIP language-and-image model shows that EAT patterns add otherwise unobservable information about the component biases that make up an EAT; reveal the effects of prompting in zero-shot models; and can also identify situations when cosine similarity is an ineffective metric, rendering an EAT unreliable. Our work contributes a method for rendering bias more observable and interpretable, improving the transparency of computational investigations into human minds and societies.

Chenjun Xu, Zhennan Zhou, Zhan Su et al.

Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking: models often generate low-yield reasoning that increases inference cost and latency. This inefficiency is especially problematic in low-data fine-tuning regimes, where real applications adapt reasoning models with limited supervision and cannot rely on large-scale teacher distillation or heavy test-time control. To address this, we propose STOP (Structured On-policy Pruning), an on-policy algorithm for analyzing and pruning long-form reasoning traces. STOP constructs self-distilled traces from the model. Then it maps each trace into a structured reasoning interface through node segmentation, taxonomy annotation, and reasoning-tree construction. On top of this interface, we introduce ECN (Earliest Correct Node), which retains the shortest prefix ending at the earliest node that both functions as an answering conclusion and yields the correct final answer, removing redundant post-solution reasoning while preserving semantic continuity. Experiments on DeepSeek-R1-Distill-Qwen-7B and DeepSeek-R1-Distill-LLaMA-3-8B across GSM8K, Math 500, and AIME 2024 show that STOP reduces generated tokens by 19.4-42.4% while largely preserving accuracy in low-data fine-tuning. Beyond efficiency, our analyses show that STOP induces much smaller distributional shift than teacher-guided pruning, improves the structural efficiency of generated reasoning, and reallocates reasoning effort away from redundant verification and backtracking toward more productive exploration.

Bingbing Wen, Bill Howe, Lucy Lu Wang · allen-ai, uw

The correct model response in the face of uncertainty is to abstain from answering a question so as not to mislead the user. In this work, we study the ability of LLMs to abstain from answering context-dependent science questions when provided insufficient or incorrect context. We probe model sensitivity in several settings: removing gold context, replacing gold context with irrelevant context, and providing additional context beyond what is given. In experiments on four QA datasets with six LLMs, we show that performance varies greatly across models, across the type of context provided, and also by question type; in particular, many LLMs seem unable to abstain from answering boolean questions using standard QA prompts. Our analysis also highlights the unexpected impact of abstention performance on QA task accuracy. Counter-intuitively, in some settings, replacing gold context with irrelevant context or adding irrelevant context to gold context can improve abstention performance in a way that results in improvements in task performance. Our results imply that changes are needed in QA dataset design and evaluation to more effectively assess the correctness and downstream impacts of model abstention.

Nicholas Clark, Hua Shen, Bill Howe et al.

LLMs increasingly serve as tools for knowledge acquisition, yet users cannot effectively specify how they want information presented. When users request that LLMs "cite reputable sources," "express appropriate uncertainty," or "include multiple perspectives," they discover that current interfaces provide no structured way to articulate these preferences. The result is prompt sharing folklore: community-specific copied prompts passed through trust relationships rather than based on measured efficacy. We propose the Epistemic Alignment Framework, a set of ten challenges in knowledge transmission derived from the philosophical literature of epistemology, concerning issues such as evidence quality assessment and calibration of testimonial reliance. The framework serves as a structured intermediary between user needs and system capabilities, creating a common vocabulary to bridge the gap between what users want and what systems deliver. Through a thematic analysis of custom prompts and personalization strategies shared on online communities where these issues are actively discussed, we find users develop elaborate workarounds to address each of the challenges. We then apply our framework to two prominent model providers, OpenAI and Anthropic, through content analysis of their documented policies and product features. Our analysis shows that while these providers have partially addressed the challenges we identified, they fail to establish adequate mechanisms for specifying epistemic preferences, lack transparency about how preferences are implemented, and offer no verification tools to confirm whether preferences were followed. For AI developers, the Epistemic Alignment Framework offers concrete guidance for supporting diverse approaches to knowledge; for users, it works toward information delivery that aligns with their specific needs rather than defaulting to one-size-fits-all approaches.

Chenjun Xu, Bingbing Wen, Bin Han et al. · allen-ai, uw

Psychology research has shown that humans are poor at estimating their performance on tasks, tending towards underconfidence on easy tasks and overconfidence on difficult tasks. We examine three LLMs, Llama-3-70B-instruct, Claude-3-Sonnet, and GPT-4o, on a range of QA tasks of varying difficulty, and show that models exhibit subtle differences from human patterns of overconfidence: less sensitive to task difficulty, and when prompted to answer based on different personas -- e.g., expert vs layman, or different race, gender, and ages -- the models will respond with stereotypically biased confidence estimations even though their underlying answer accuracy remains the same. Based on these observations, we propose Answer-Free Confidence Estimation (AFCE) to improve confidence calibration and LLM interpretability in these settings. AFCE is a self-assessment method that employs two stages of prompting, first eliciting only confidence scores on questions, then asking separately for the answer. Experiments on the MMLU and GPQA datasets spanning subjects and difficulty show that this separation of tasks significantly reduces overconfidence and delivers more human-like sensitivity to task difficulty.

Bingbing Wen, Zhengyuan Yang, Jianfeng Wang et al.

In this paper, we build a visual dialogue dataset, named InfoVisDial, which provides rich informative answers in each round even with external knowledge related to the visual content. Different from existing datasets where the answer is compact and short, InfoVisDial contains long free-form answers with rich information in each round of dialogue. For effective data collection, the key idea is to bridge the large-scale multimodal model (e.g., GIT) and the language models (e.g., GPT-3). GIT can describe the image content even with scene text, while GPT-3 can generate informative dialogue based on the image description and appropriate prompting techniques. With such automatic pipeline, we can readily generate informative visual dialogue data at scale. Then, we ask human annotators to rate the generated dialogues to filter the low-quality conversations.Human analyses show that InfoVisDial covers informative and diverse dialogue topics: $54.4\%$ of the dialogue rounds are related to image scene texts, and $36.7\%$ require external knowledge. Each round's answer is also long and open-ended: $87.3\%$ of answers are unique with an average length of $8.9$, compared with $27.37\%$ and $2.9$ in VisDial. Last, we propose a strong baseline by adapting the GIT model for the visual dialogue task and fine-tune the model on InfoVisDial. Hopefully, our work can motivate more effort on this direction.

Bin Han, Robert Wolfe, Anat Caspi et al.

We explore the application of large language models (LLMs) to empower domain experts in integrating large, heterogeneous, and noisy urban spatial datasets. Traditional rule-based integration methods are unable to cover all edge cases, requiring manual verification and repair. Machine learning approaches require collecting and labeling of large numbers of task-specific samples. In this study, we investigate the potential of LLMs for spatial data integration. Our analysis first considers how LLMs reason about environmental spatial relationships mediated by human experience, such as between roads and sidewalks. We show that while LLMs exhibit spatial reasoning capabilities, they struggle to connect the macro-scale environment with the relevant computational geometry tasks, often producing logically incoherent responses. But when provided relevant features, thereby reducing dependence on spatial reasoning, LLMs are able to generate high-performing results. We then adapt a review-and-refine method, which proves remarkably effective in correcting erroneous initial responses while preserving accurate responses. We discuss practical implications of employing LLMs for spatial data integration in real-world contexts and outline future research directions, including post-training, multi-modal integration methods, and support for diverse data formats. Our findings position LLMs as a promising and flexible alternative to traditional rule-based heuristics, advancing the capabilities of adaptive spatial data integration.

Yiwei Yang, Chung Peng Lee, Shangbin Feng et al.

Finetuning can cause spurious correlations to arise between non-essential features and the target labels, but benchmarks to study these effects involve contrived settings and narrow tasks. In contrast, we consider spurious correlations in multi-modal Large Vision Language Models (LVLMs) pretrained on extensive and diverse datasets without explicit task supervision. We develop a benchmark by sourcing GPT-4o errors on real-world visual-question-answering (VQA) benchmarks, then curating a subset through LVLM-human annotation and synthetic counterfactual evaluation to identify errors caused by spurious correlations. This process yields SpuriVerse, a novel benchmark comprised of 124 distinct types of spurious correlations extracted from real-world datasets, each containing 1 realistic and 10 synthetic VQA samples for a total of 1364 multiple choice questions. We evaluate 15 open and closed-source LVLMs on SpuriVerse, finding that even state-of-the-art closed-source models struggle significantly, achieving at best only 37.1% accuracy. Fine-tuning on synthetic examples that emphasize the spurious correlation improves performance to 78.40%, suggesting that training on diverse spurious patterns generalizes to unseen situations: models appear to learn to avoid "shortcuts" and attend to the overall image context.

Yuxiang Zhang, Bill Howe, Anat Caspi

While advances in mobility technology including autonomous vehicles and multi-modal navigation systems can improve mobility equity for people with disabilities, these technologies depend crucially on accurate, standardized, and complete pedestrian path networks. Ad hoc collection efforts lead to a data record that is sparse, unreliable, and non-interoperable. This paper presents a sociotechnical methodology to collect, manage, serve, and maintain pedestrian path data at a statewide scale. Combining the automation afforded by computer-vision approaches applied to aerial imagery and existing road network data with the quality control afforded by interactive tools, we aim to produce routable pedestrian pathways for the entire State of Washington within approximately two years. We extract paths, crossings, and curb ramps at scale from aerial imagery, integrating multi-input segmentation methods with road topology data to ensure connected, routable networks. We then organize the predictions into project regions selected for their value to the public interest, where each project region is divided into intersection-scale tasks. These tasks are assigned and tracked through an interactive tool that manages concurrency, progress, feedback, and data management. We demonstrate that our automated systems outperform state-of-the-art methods in producing routable pathway networks, which then significantly reduces the time required for human vetting. Our results demonstrate the feasibility of yielding accurate, robust pedestrian pathway networks at the scale of an entire state. This paper intends to inform procedures for national-scale ADA compliance by providing pedestrian equity, safety, and accessibility, and improving urban environments for all users.

Lucas Rosenblatt, Bin Han, Robert Wolfe et al.

Large language models (LLMs) can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumptions, including attacker access to entire samples or long, ordered prefixes, leaving open the question of how vulnerable LLMs are when adversaries have only partial, unordered sample information. For example, if an attacker knows a patient has "hypertension," under what conditions can they query a model fine-tuned on patient data to learn the patient also has "osteoarthritis?" In this paper, we introduce a more general threat model under this weaker assumption and show that fine-tuned LLMs are susceptible to these fragment-specific extraction attacks. To systematically investigate these attacks, we propose two data-blind methods: (1) a likelihood ratio attack inspired by methods from membership inference, and (2) a novel approach, PRISM, which regularizes the ratio by leveraging an external prior. Using examples from both medical and legal settings, we show that both methods are competitive with a data-aware baseline classifier that assumes access to labeled in-distribution data, underscoring their robustness.

Babak Salimi, Bill Howe, Dan Suciu

Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflects discrimination, suggesting a data management problem. In this paper, we first make a distinction between associational and causal definitions of fairness in the literature and argue that the concept of fairness requires causal reasoning. We then review existing works and identify future opportunities for applying data management techniques to causal algorithmic fairness.

Sean Yang, Po-shen Lee, Jevin D. West et al.

Figures are an important channel for scientific communication, used to express complex ideas, models and data in ways that words cannot. However, this visual information is mostly ignored in analyses of the scientific literature. In this paper, we demonstrate the utility of using scientific figures as markers of knowledge domains in science, which can be used for classification, recommender systems, and studies of scientific information exchange. We encode sets of images into a visual signature, then use distances between these signatures to understand how patterns of visual communication compare with patterns of jargon and citation structures. We find that figures can be as effective for differentiating communities of practice as text or citation patterns. We then consider where these metrics disagree to understand how different disciplines use visualization to express ideas. Finally, we further consider how specific figure types propagate through the literature, suggesting a new mechanism for understanding the flow of ideas apart from conventional channels of text and citations. Our ultimate aim is to better leverage these information-dense objects to improve scientific communication across disciplinary boundaries.

An Yan, Bill Howe

Emerging transportation modes, including car-sharing, bike-sharing, and ride-hailing, are transforming urban mobility but have been shown to reinforce socioeconomic inequities. Spatiotemporal demand prediction models for these new mobility regimes must therefore consider fairness as a first-class design requirement. We present FairST, a fairness-aware model for predicting demand for new mobility systems. Our approach utilizes 1D, 2D and 3D convolutions to integrate various urban features and learn the spatial-temporal dynamics of a mobility system, but we include fairness metrics as a form of regularization to make the predictions more equitable across demographic groups. We propose two novel spatiotemporal fairness metrics, a region-based fairness gap (RFG) and an individual-based fairness gap (IFG). Both quantify equity in a spatiotemporal context, but vary by whether demographics are labeled at the region level (RFG) or whether population distribution information is available (IFG). Experimental results on real bike share and ride share datasets demonstrate the effectiveness of the proposed model: FairST not only reduces the fairness gap by more than 80%, but can surprisingly achieve better accuracy than state-of-the-art yet fairness-oblivious methods including LSTMs, ConvLSTMs, and 3D CNN.

Babak Salimi, Luke Rodriguez, Bill Howe et al.

Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem. Existing treatments of fairness rely on statistical correlations that can be fooled by statistical anomalies, such as Simpson's paradox. Proposals for causality-based definitions of fairness can correctly model some of these situations, but they require specification of the underlying causal models. In this paper, we formalize the situation as a database repair problem, proving sufficient conditions for fair classifiers in terms of admissible variables as opposed to a complete causal model. We show that these conditions correctly capture subtle fairness violations. We then use these conditions as the basis for database repair algorithms that provide provable fairness guarantees about classifiers trained on their training labels. We evaluate our algorithms on real data, demonstrating improvement over the state of the art on multiple fairness metrics proposed in the literature while retaining high utility.

Sean T. Yang, Kuan-Hao Huang, Bill Howe

We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise frequently in high-value applications where structured training data is expensive to produce, but free-text descriptions are common. JECL trains by minimizing the Kullback-Leibler divergence between the distribution of the images and text to that of a combined joint target distribution and optimizing the Jensen-Shannon divergence between the soft cluster assignments of the images and text. Regularizers are also applied to JECL to prevent trivial solutions. Experiments show that JECL outperforms both single-view and multi-view methods on large benchmark image-caption datasets, and is remarkably robust to missing captions and varying data sizes.

Ke Yang, Julia Stoyanovich, Abolfazl Asudeh et al.

Algorithmic decisions often result in scoring and ranking individuals to determine credit worthiness, qualifications for college admissions and employment, and compatibility as dating partners. While automatic and seemingly objective, ranking algorithms can discriminate against individuals and protected groups, and exhibit low diversity. Furthermore, ranked results are often unstable --- small changes in the input data or in the ranking methodology may lead to drastic changes in the output, making the result uninformative and easy to manipulate. Similar concerns apply in cases where items other than individuals are ranked, including colleges, academic departments, or products. In this demonstration we present Ranking Facts, a Web-based application that generates a "nutritional label" for rankings. Ranking Facts is made up of a collection of visual widgets that implement our latest research results on fairness, stability, and transparency for rankings, and that communicate details of the ranking methodology, or of the output, to the end user. We will showcase Ranking Facts on real datasets from different domains, including college rankings, criminal risk assessment, and financial services.

Shrainik Jain, Bill Howe, Jiaqi Yan et al.

We consider methods for learning vector representations of SQL queries to support generalized workload analytics tasks, including workload summarization for index selection and predicting queries that will trigger memory errors. We consider vector representations of both raw SQL text and optimized query plans, and evaluate these methods on synthetic and real SQL workloads. We find that general algorithms based on vector representations can outperform existing approaches that rely on specialized features. For index recommendation, we cluster the vector representations to compress large workloads with no loss in performance from the recommended index. For error prediction, we train a classifier over learned vectors that can automatically relate subtle syntactic patterns with specific errors raised during query execution. Surprisingly, we also find that these methods enable transfer learning, where a model trained on one SQL corpus can be applied to an unrelated corpus and still enable good performance. We find that these general approaches, when trained on a large corpus of SQL queries, provides a robust foundation for a variety of workload analysis tasks and database features, without requiring application-specific feature engineering.

Maxim Grechkin, Hoifung Poon, Bill Howe

Many real-world applications require automated data annotation, such as identifying tissue origins based on gene expressions and classifying images into semantic categories. Annotation classes are often numerous and subject to changes over time, and annotating examples has become the major bottleneck for supervised learning methods. In science and other high-value domains, large repositories of data samples are often available, together with two sources of organic supervision: a lexicon for the annotation classes, and text descriptions that accompany some data samples. Distant supervision has emerged as a promising paradigm for exploiting such indirect supervision by automatically annotating examples where the text description contains a class mention in the lexicon. However, due to linguistic variations and ambiguities, such training data is inherently noisy, which limits the accuracy of this approach. In this paper, we introduce an auxiliary natural language processing system for the text modality, and incorporate co-training to reduce noise and augment signal in distant supervision. Without using any manually labeled data, our EZLearn system learned to accurately annotate data samples in functional genomics and scientific figure comprehension, substantially outperforming state-of-the-art supervised methods trained on tens of thousands of annotated examples.

Po-shen Lee, Jevin D. West, Bill Howe

Scientific results are communicated visually in the literature through diagrams, visualizations, and photographs. These information-dense objects have been largely ignored in bibliometrics and scientometrics studies when compared to citations and text. In this paper, we use techniques from computer vision and machine learning to classify more than 8 million figures from PubMed into 5 figure types and study the resulting patterns of visual information as they relate to impact. We find that the distribution of figures and figure types in the literature has remained relatively constant over time, but can vary widely across field and topic. Remarkably, we find a significant correlation between scientific impact and the use of visual information, where higher impact papers tend to include more diagrams, and to a lesser extent more plots and photographs. To explore these results and other ways of extracting this visual information, we have built a visual browser to illustrate the concept and explore design alternatives for supporting viziometric analysis and organizing visual information. We use these results to articulate a new research agenda -- viziometrics -- to study the organization and presentation of visual information in the scientific literature.