Conformal Prediction (CP) is a popular method for uncertainty quantification with machine learning models. While conformal prediction provides probabilistic guarantees regarding the coverage of the true label, these guarantees are agnostic to the presence of sensitive attributes within the dataset. In this work, we formalize \textit{Conformal Fairness}, a notion of fairness using conformal predictors, and provide a theoretically well-founded algorithm and associated framework to control for the gaps in coverage between different sensitive groups. Our framework leverages the exchangeability assumption (implicit to CP) rather than the typical IID assumption, allowing us to apply the notion of Conformal Fairness to data types and tasks that are not IID, such as graph data. Experiments were conducted on graph and tabular datasets to demonstrate that the algorithm can control fairness-related gaps in addition to coverage aligned with theoretical expectations.

Recent advances in time series research have created a significant demand for better time series visualization techniques, especially for large-scale datasets that contain millions of time series or more. In this paper, we consider a common use scenario where analysts aim to identify representative time series from a large collection. These representative time series generalize as many time series as possible and can be used for downstream tasks. Building a visualization system for this scenario involves many challenges, including visualizing, selecting, and highlighting a subset of time series from the overall dataset. Moreover, the potential for time series to be incomplete due to missing records adds an extra layer of difficulty. To address these challenges, we propose a novel visualization system, called the Locality Sensitive Hashing-based Interactive Visualization Explorer for large-scale Incomplete Time Series (LIVE-ITS). On the frontend, LIVE-ITS allows analysts to interact with the system and select representative time series in areas of interest. In the backend, LIVE-ITS not only selects an optimal subset that represents as many time series as possible, but also achieves the best possible time complexity. Experiments on both synthetic dataset and real-world datasets show that LIVE-ITS exhibits high partition accuracy and high response efficiency, further validating the effectiveness of our proposed visualization system.

A sizable proportion of deployed machine learning models make their decisions in a black-box manner. Such decision-making procedures are susceptible to intrinsic biases, which has led to a call for accountability in deployed decision systems. In this work, we investigate mechanisms that help audit claimed mathematical guarantees of the fairness of such systems. We construct AVOIR, a system that reduces the number of observations required for the runtime monitoring of probabilistic assertions over fairness metrics specified on decision functions associated with black-box AI models. AVOIR provides an adaptive process that automates the inference of probabilistic guarantees associated with estimating a wide range of fairness metrics. In addition, AVOIR enables the exploration of fairness violations aligned with governance and regulatory requirements. We conduct case studies with fairness metrics on three different datasets and demonstrate how AVOIR can help detect and localize fairness violations and ameliorate the issues with faulty fairness metric design.

Darknet market forums are frequently used to exchange illegal goods and services between parties who use encryption to conceal their identities.The Tor network is used to host these markets, which guarantees additional anonymization from IP and location tracking, making it challenging to link across malicious users using multiple accounts (sybils).Additionally, users migrate to new forums when one is closed further increasing the difficulty of linking users across multiple forums.We develop a novel stylometry-based multitask learning approach for natural language and model interactions using graph embeddings to construct low-dimensional representations of short episodes of user activity for authorship attribution.We provide a comprehensive evaluation of our methods across four different darknet forums demonstrating its efficacy over the state-of-the-art, with a lift of up to 2.5X on Mean Retrieval Rank and 2X on Recall@10.

Accurately discovering user intents from their written or spoken language plays a critical role in natural language understanding and automated dialog response. Most existing research models this as a classification task with a single intent label per utterance. Going beyond this formulation, we define and investigate a new problem of open intent discovery. It involves discovering one or more generic intent types from text utterances, that may not have been encountered during training. We propose a novel, domain-agnostic approach, OPINE, which formulates the problem as a sequence tagging task in an open-world setting. It employs a CRF on top of a bidirectional LSTM to extract intents in a consistent format, subject to constraints among intent tag labels. We apply multi-headed self-attention and adversarial training to effectively learn dependencies between distant words, and robustly adapt our model across varying domains. We also curate and release an intent-annotated dataset of 25K real-life utterances spanning diverse domains. Extensive experiments show that OPINE outperforms state-of-art baselines by 5-15% F1 score.

We introduce LEAF-QA, a comprehensive dataset of 250,000 densely annotated figures/charts, constructed from real-world open data sources, along with 2 million question-answer (QA) pairs querying the structure and semantics of these charts. LEAF-QA highlights the problem of multimodal QA, which is notably different from conventional visual QA (VQA), and has recently gained interest in the community. Furthermore, LEAF-QA is significantly more complex than previous attempts at chart QA, viz. FigureQA and DVQA, which present only limited variations in chart data. LEAF-QA being constructed from real-world sources, requires a novel architecture to enable question answering. To this end, LEAF-Net, a deep architecture involving chart element localization, question and answer encoding in terms of chart elements, and an attention network is proposed. Different experiments are conducted to demonstrate the challenges of QA on LEAF-QA. The proposed architecture, LEAF-Net also considerably advances the current state-of-the-art on FigureQA and DVQA.

Accurately discovering user intents from their written or spoken language plays a critical role in natural language understanding and automated dialog response. Most existing research models this as a classification task with a single intent label per utterance, grouping user utterances into a single intent type from a set of categories known beforehand. Going beyond this formulation, we define and investigate a new problem of open intent discovery. It involves discovering one or more generic intent types from text utterances, that may not have been encountered during training. We propose a novel domain-agnostic approach, OPINE, which formulates the problem as a sequence tagging task under an open-world setting. It employs a CRF on top of a bidirectional LSTM to extract intents in a consistent format, subject to constraints among intent tag labels. We apply a multi-head self-attention mechanism to effectively learn dependencies between distant words. We further use adversarial training to improve performance and robustly adapt our model across varying domains. Finally, we curate and plan to release an open intent annotated dataset of 25K real-life utterances spanning diverse domains. Extensive experiments show that our approach outperforms state-of-the-art baselines by 5-15% F1 score points. We also demonstrate the efficacy of OPINE in recognizing multiple, diverse domain intents with limited (can also be zero) training examples per unique domain.

Natural disasters such as floods, forest fires, and hurricanes can cause catastrophic damage to human life and infrastructure. We focus on response to hurricanes caused by both river water flooding and storm surge. Using models for storm surge simulation and flood extent prediction, we generate forecasts about areas likely to be highly affected by the disaster. Further, we overlay the simulation results with information about traffic incidents to correlate traffic incidents with other data modality. We present these results in a modularized, interactive map-based visualization, which can help emergency responders to better plan and coordinate disaster response.

Dynamically extracting and representing continually evolving knowledge entities is an essential scaffold for grounded intelligence and decision making. Creating knowledge schemas for newly emerging, unfamiliar, domain-specific ideas or events poses the following challenges: (i) detecting relevant, often previously unknown concepts associated with the new domain; and (ii) learning ontological, semantically accurate relationships among the new concepts, despite having severely limited annotated data. To this end, we propose a novel LSTM-based framework with attentive pooling, BOLT-K, to learn an ontology for a target subject or domain. We bootstrap our ontology learning approach by adapting and transferring knowledge from an existing, functionally related source domain. We also augment the inadequate labeled data available for the target domain with various strategies to minimize human expertise during model development and training. BOLT-K first employs semantic and graphical features to recognize the entity or concept pairs likely to be related to each other, and filters out spurious concept combinations. It is then jointly trained on knowledge from the target and source domains to learn relationships among the target concepts. The target concepts and their corresponding relationships are subsequently used to construct an ontology. We extensively evaluate our framework on several, real-world bio-medical and commercial product domain ontologies. We obtain significant improvements of 5-25% F1-score points over state-of-the-art baselines. We also examine the potential of BOLT-K in detecting the presence of novel kinds of relationships that were unseen during training.

Enterprise content writers are engaged in writing textual content for various purposes. Often, the text being written may already be present in the enterprise corpus in the form of past articles and can be re-purposed for the current needs. In the absence of suitable tools, authors manually curate/create such content (sometimes from scratch) which reduces their productivity. To address this, we propose an automatic approach to generate an initial version of the author’s intended text based on an input content snippet. Starting with a set of extracted textual fragments related to the snippet based on the query words in it, the proposed approach builds the desired text from these fragment by simultaneously optimizing the information coverage, relevance, diversity and coherence in the generated content. Evaluations on standard datasets shows improved performance against existing baselines on several metrics.