Harper Hua, Zhen Han, Zhengyuan Shen, Meng-Chieh Lee, Sheng Guan, Qi Zhu, Sullam Jeoung, Yueyan Chen, Yunfei Bai, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han, Soji Adeshina, Vassilis N. Ioannidis, Huzefa Rangwala, Christos Faloutsos. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Graph Neural Networks (GNNs) are susceptible to distribution shifts, creating vulnerability and security issues in critical domains. There is a pressing need to enhance the generalizability of GNNs on out-of-distribution (OOD) test data. Existing methods that target learning an invariant (feature, structure)-label mapping often depend on oversimplified assumptions about the data generation process, which do not adequately reflect the actual dynamics of distribution shifts in graphs. In this paper, we introduce a more realistic graph data generation model using Structural Causal Models (SCMs), allowing us to redefine distribution shifts by pinpointing their origins within the generation process. Building on this, we propose a casual decoupling framework, DeCaf, that independently learns unbiased feature-label and structure-label mappings. We provide a detailed theoretical framework that shows how our approach can effectively mitigate the impact of various distribution shifts. We evaluate DeCaf across both real-world and synthetic datasets that demonstrate different patterns of shifts, confirming its efficacy in enhancing the generalizability of GNNs. Our code is available at: \url{https://github.com/hanxiaoxue114/DeCaf-GraphOOD.}

Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis, Zhen Han, Qi Zhu, Ian Robinson, Bryan Thompson, Huzefa Rangwala, George Karypis. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Tabular data within enterprises or open data repositories provide a huge opportunity for feature augmentation. Using these data sources to augment training data often boosts model performance, which is crucial in data-centric AutoML systems. Recent works on automatic feature augmentation have limited capabilities in utilizing useful features that cannot be joined with the base table without connecting through intermediate tables. We present Featpilot, a novel framework that explores and integrates high-quality features in tabular data for ML models. Featpilot evaluates a candidate feature from two aspects: (1) the efficacy of a join path connecting the feature to the base table and (2) the intrinsic value of a feature towards an ML task. Featpilot efficiently identifies high-quality features and their optimized join paths to augment the base table. Our experimental results show that Featpilot achieves up to a 10.27% improvement in ML model performance compared to state-of-the-art solutions across six public datasets.

Autonomy via agents based on large language models (LLMs) that can carry out personalized yet standardized tasks presents a significant opportunity to drive human efficiency. There is an emerging need and interest in automating web tasks (e.g., booking a hotel for a given date within a budget). Being a practical use case itself, the web agent also serves as an important proof-of-concept example for various agent grounding scenarios, with its success promising advancements in many future applications. Meanwhile, much prior research focuses on handcrafting their web agent strategies (e.g., agent's prompting templates, reflective workflow, role-play and multi-agent systems, search or sampling methods, etc.) and the corresponding in-context examples. However, these custom strategies often struggle with generalizability across all potential real-world applications. On the other hand, there has been limited study on the misalignment between a web agent's observation and action representation, and the data on which the agent's underlying LLM has been pre-trained. This discrepancy is especially notable when LLMs are primarily trained for language completion rather than tasks involving embodied navigation actions and symbolic web elements. In our study, we enhance an LLM-based web agent by simply refining its observation and action space, aligning these more closely with the LLM's capabilities. This approach enables our base agent to significantly outperform previous methods on a wide variety of web tasks. Specifically, on WebArena, a benchmark featuring general-purpose web interaction tasks, our agent AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively, and boosts the success rate by 26.6 points (+161%) over similar plain web agents with its observation and action space alignment. Furthermore, on WebVoyager benchmark comprising tasks defined on real-world websites, AgentOccam exceeds the former best agent by 2.4 points (+4.6%) on tasks with deterministic answers. We achieve this without using in-context examples, new agent roles, online feedback or search strategies. AgentOccam's simple design highlights LLMs' impressive zero-shot performance on web tasks, and underlines the critical role of carefully tuning observation and action spaces for LLM-based agents.

Recent years have witnessed significant advancements in graph machine learning (GML), with its applications spanning numerous domains. However, the focus of GML has predominantly been on developing powerful models, often overlooking a crucial initial step: constructing suitable graphs from common data formats, such as tabular data. This construction process is fundamental to applying graph-based models, yet it remains largely understudied and lacks formalization. Our research aims to address this gap by formalizing the graph construction problem and proposing an effective solution. We identify two critical challenges to achieve this goal: 1. The absence of dedicated datasets to formalize and evaluate the effectiveness of graph construction methods, and 2. Existing automatic construction methods can only be applied to some specific cases, while tedious human engineering is required to generate high-quality graphs. To tackle these challenges, we present a two-fold contribution. First, we introduce a set of datasets to formalize and evaluate graph construction methods. Second, we propose an LLM-based solution, AutoG, automatically generating high-quality graph schemas without human intervention. The experimental results demonstrate that the quality of constructed graphs is critical to downstream task performance, and AutoG can generate high-quality graphs that rival those produced by human experts. Our code can be accessible from https://github.com/amazon-science/Automatic-Table-to-Graph-Generation.

The ability to construct transferable descriptors for molecular and biological systems has broad applications in drug discovery, molecular dynamics, and protein analysis. Geometric graph neural networks (Geom-GNNs) utilizing all-atom information have revolutionized atomistic simulations by enabling the prediction of interatomic potentials and molecular properties. Despite these advances, the application of all-atom Geom-GNNs in protein modeling remains limited due to computational constraints. In this work, we first demonstrate the potential of pre-trained Geom-GNNs as zero-shot transfer learners, effectively modeling protein systems with all-atom granularity. Through extensive experimentation to evaluate their expressive power, we characterize the scaling behaviors of Geom-GNNs across self-supervised, supervised, and unsupervised setups. Interestingly, we find that Geom-GNNs deviate from conventional power-law scaling observed in other domains, with no predictable scaling principles for molecular representation learning. Furthermore, we show how pre-trained graph embeddings can be directly used for analysis and synergize with other architectures to enhance expressive power for protein modeling.

Recent years have witnessed a surge in the development of protein structural tokenization methods, which chunk protein 3D structures into discrete or continuous representations. Structure tokenization enables the direct application of powerful techniques like language modeling for protein structures, and large multimodal models to integrate structures with protein sequences and functional texts. Despite the progress, the capabilities and limitations of these methods remain poorly understood due to the lack of a unified evaluation framework. We first introduce StructTokenBench, a framework that comprehensively evaluates the quality and efficiency of structure tokenizers, focusing on fine-grained local substructures rather than global structures, as typical in existing benchmarks. Our evaluations reveal that no single model dominates all benchmarking perspectives. Observations of codebook under-utilization led us to develop AminoAseed, a simple yet effective strategy that enhances codebook gradient updates and optimally balances codebook size and dimension for improved tokenizer utilization and quality. Compared to the leading model ESM3, our method achieves an average of 6.31% performance improvement across 24 supervised tasks, with sensitivity and utilization rates increased by 12.83% and 124.03%, respectively. Source code and model weights are available at https://github.com/KatarinaYuan/StructTokenBench.

Frontier large language models (LLMs) have demonstrated remarkable performance across various knowledge-intensive enterprise tasks. However, these models are primarily trained on unstructured, general knowledge, which limits their effectiveness in domain-specific applications-particularly when tasks involve structured data sources or sensitive enterprise information. We propose the first Structured Knowledge for Large Language Models Workshop - SKnow-LLM, which aims to bridge this gap by promoting research on innovative methodologies and practical applications in this area. Through keynote talks, panel discussions and paper presentations, the workshop will foster in-depth discussions on recent advances, identify existing challenges, and explore promising directions for integrating structured knowledge into LLMs.

Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents. We close this gap with the Hierarchical Lexical Graph (HLG), a three-tier index that (i) traces every atomic proposition to its source(ii) clusters propositions into latent topics, and (iii) links entities and relations to expose cross-document paths. On top of HLG we build two complementary, plug-and-play retrievers: StatementGraphRAG, which performs fine-grained entity-aware beam search over propositions for high-precision factoid questions, and TopicGraphRAG, which selects coarse topics before expanding along entity links to supply broad yet relevant context for exploratory queries. Additionally, existing benchmarks lack the complexity required to rigorously evaluate multi-hop summarization systems, often focusing on single-document queries or limited datasets. To address this, we introduce a synthetic dataset generation pipeline that curates realistic, multi-document question-answer pairs, enabling robust evaluation of multi-hop retrieval systems. Extensive experiments across five datasets demonstrate that our methods outperform naive chunk-based RAG, achieving an average relative improvement of 23.1% in retrieval recall and correctness. Open-source Python library is available at https://github.com/awslabs/graphrag-toolkit.

Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when handling multimodal data. We introduce MLZero, a novel multi-agent framework powered by Large Language Models (LLMs) that enables end-to-end ML automation across diverse data modalities with minimal human intervention. A cognitive perception module is first employed, transforming raw multimodal inputs into perceptual context that effectively guides the subsequent workflow. To address key limitations of LLMs, such as hallucinated code generation and outdated API knowledge, we enhance the iterative code generation process with semantic and episodic memory. MLZero demonstrates superior performance on MLE-Bench Lite, outperforming all competitors in both success rate and solution quality, securing six gold medals. Furthermore, when evaluated on our Multimodal AutoML Agent Benchmark, which includes 25 more challenging tasks spanning diverse data modalities, MLZero outperforms the competing methods by a large margin with a success rate of 0.92 (+263.6\%) and an average rank of 2.28. Our approach maintains its robust effectiveness even with a compact 8B LLM, outperforming full-size systems from existing solutions.

Since the seminal work of TabPFN, research on tabular foundation models (TFMs) based on in-context learning (ICL) has challenged long-standing paradigms in machine learning. Without seeing any real-world data, models pretrained on purely synthetic datasets generalize remarkably well across diverse datasets, often using only a moderate number of in-context examples. This shifts the focus in tabular machine learning from model architecture design to the design of synthetic datasets, or, more precisely, to the prior distributions that generate them. Yet the guiding principles for prior design remain poorly understood. This work marks the first attempt to address the gap. We systematically investigate and identify key properties of synthetic priors that allow pretrained TFMs to generalize well. Based on these insights, we introduce Mitra, a TFM trained on a curated mixture of synthetic priors selected for their diversity, distinctiveness, and performance on real-world tabular data. Mitra consistently outperforms state-of-the-art TFMs, such as TabPFNv2 and TabICL, across both classification and regression benchmarks, with better sample efficiency.

Costas Mavromatis, Balasubramaniam Srinivasan, Zhengyuan Shen, Jiani Zhang, Huzefa Rangwala, Christos Faloutsos, George Karypis. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

How can we effectively generate missing data transformations among tables in a data repository? Multiple versions of the same tables are generated from the iterative process when data scientists and machine learning engineers fine-tune their ML pipelines, making incremental improvements. This process often involves data transformation and augmentation that produces an augmented table based on its base version and related tables. However, data transformations are often not well-documented or completely missing, resulting in poor traceability, reproducibility and explainability of ML pipelines. In this paper, we propose DATALoRE, a framework that explains data changes between an initial dataset and its augmented version to improves traceability. Given a base table, DATALoRE first discovers its potentially related tables from the data repository using a variety of data discovery techniques. DATALoRE then effectively leverages a large language model (LLM) to generate a variety of data transformations that lead to the augmented table. DATALoRE validates these transformations and selects the minimum number of related tables to ensure traceability and reproducibility of the ML pipelines. A preliminary experiment shows that DATALoRE is able to effectively recovery data transformations on two benchmark datasets.

Foundation models (FMs) learn from large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks. However, FMs developed for biomedical domains have largely remained unimodal, i.e., independently trained and used for tasks on protein sequences alone, small molecule structures alone, or clinical data alone. To overcome this limitation, we present BioBridge, a parameter-efficient learning framework, to bridge independently trained unimodal FMs to establish multimodal behavior. BioBridge achieves it by utilizing Knowledge Graphs (KG) to learn transformations between one unimodal FM and another without fine-tuning any underlying unimodal FMs. Our results demonstrate that BioBridge can beat the best baseline KG embedding methods (on average by ~ 76.3%) in cross-modal retrieval tasks. We also identify BioBridge demonstrates out-of-domain generalization ability by extrapolating to unseen modalities or relations. Additionally, we also show that BioBridge presents itself as a general-purpose retriever that can aid biomedical multimodal question answering as well as enhance the guided generation of novel drugs. Code is at https://github.com/RyanWangZf/BioBridge.

Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use a retriever that fetches relevant information to expand LLM's knowledge scope. However, existing textual-oriented retrieval-based LLMs are not ideal on structured table data due to diversified data modalities and large table sizes. In this work, we propose OpenTab, an open-domain table reasoning framework powered by LLMs. Overall, OpenTab leverages table retriever to fetch relevant tables and then generates SQL programs to parse the retrieved tables efficiently. Utilizing the intermediate data derived from the SQL executions, it conducts grounded inference to produce accurate response. Extensive experimental evaluation shows that OpenTab significantly outperforms baselines in both open- and closed-domain settings, achieving up to 21.5% higher accuracy. We further run ablation studies to validate the efficacy of our proposed designs of the system.

Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces TabSyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capturing inter-column relations; (2) Quality: optimizing the distribution of latent embeddings to enhance the subsequent training of diffusion models, which helps generate high-quality synthetic data; (3) Speed: much fewer number of reverse steps and faster synthesis speed than existing diffusion-based methods. Extensive experiments on six datasets with five metrics demonstrate that Tabsyn outperforms existing methods. Specifically, it reduces the error rates by 86% and 67% for column-wise distribution and pair-wise column correlation estimations compared with the most competitive baselines. The code has been made available at https://github.com/amazon-science/tabsyn.

Graph machine learning (GML) is effective in many business applications. However, making GML easy to use and applicable to industry applications with massive datasets remain challenging. We developed GraphStorm, which provides an end-to-end solution for scalable graph construction, graph model training and inference. GraphStorm has the following desirable properties: (a) Easy to use: it can perform graph construction and model training and inference with just a single command; (b) Expert-friendly: GraphStorm contains many advanced GML modeling techniques to handle complex graph data and improve model performance; (c) Scalable: every component in GraphStorm can operate on graphs with billions of nodes and can scale model training and inference to different hardware without changing any code. GraphStorm has been used and deployed for over a dozen billion-scale industry applications after its release in May 2023. It is open-sourced in Github: https://github.com/awslabs/graphstorm.

Recent advances in large language models have revolutionized many sectors, including the database industry.One common challenge when dealing with large volumes of tabular data is the pervasive use of abbreviated column names, which can negatively impact performance on various data search, access, and understanding tasks.To address this issue, we introduce a new task, called NAMEGUESS, to expand column names (used in database schema) as a natural language generation problem.We create a training dataset of 384K abbreviatedexpanded column pairs using a new data fabrication method and a human-annotated evaluation benchmark that includes 9.2K examples from real-world tables.To tackle the complexities associated with polysemy and ambiguity in NAMEGUESS, we enhance autoregressive language models by conditioning on table content and column header namesyielding a fine-tuned model (with 2.7B parameters) that matches human performance.Furthermore, we conduct a comprehensive analysis (on multiple LLMs) to validate the effectiveness of table content in NAMEGUESS and identify promising future opportunities.Code has been made available at https://github. com/amazon-science/nameguess.

While using vast amounts of training data and sophisticated models has enhanced the predictive performance of Machine Learning (ML) and Artificial Intelligence (AI) solutions, it has also led to an increased difficulty in comprehending their predictions. The ability to explain predictions is often one of the primary desiderata for adopting AI and ML solutions [6, 13]. The desire for explainability has led to a rapidly growing body of literature on explainable AI (XAI) and has also resulted in the development of hundreds of XAI methods targeting different domains (e.g., finance, healthcare), applications (e.g., model debugging, actionable recourse), data modalities (e.g., tabular data, images), models (e.g., transformers, convolutional neural networks) and stakeholders (e.g., end-users, regulatory authorities, data scientists). The goal of this tutorial is to present a comprehensive overview of the XAI field to the participants. As a hands-on tutorial, we will showcase state-of-the-art methods that can be used for different data modalities and contexts to extract the right abstractions for interpretation. We will also cover common pitfalls when using explanations, e.g., misrepresentation, and lack of robustness of explanations.

Individual-level data (microdata) that characterizes a population, is essential for studying many real-world problems. However, acquiring such data is not straightforward due to cost and privacy constraints, and access is often limited to aggregated data (macro data) sources. In this study, we examine synthetic data generation as a tool to extrapolate difficult-to-obtain high-resolution data by combining information from multiple easier-to-obtain lower-resolution data sources. In particular, we introduce a framework that uses a combination of univariate and multivariate frequency tables from a given target geographical location in combination with frequency tables from other auxiliary locations to generate synthetic microdata for individuals in the target location. Our method combines the estimation of a dependency graph and conditional probabilities from the target location with the use of a Gaussian copula to leverage the available information from the auxiliary locations. We perform extensive testing on two real-world datasets and demonstrate that our approach outperforms prior approaches in preserving the overall dependency structure of the data while also satisfying the constraints defined on the different variables.

Transliteration is very common on social media, but transliterated text is not adequately handled by modern neural models for various NLP tasks. In this work, we combine data augmentation approaches with a Teacher-Student training scheme to address this issue in a cross-lingual transfer setting for fine-tuning state-of-the-art pre-trained multilingual language models such as mBERT and XLM-R. We evaluate our method on transliterated Hindi and Malayalam, also introducing new datasets for benchmarking on real-world scenarios: one on sentiment classification in transliterated Malayalam, and another on crisis tweet classification in transliterated Hindi and Malayalam (related to the 2013 North India and 2018 Kerala floods). Our method yielded an average improvement of +5.6% on mBERT and +4.7% on XLM-R in F1 scores over their strong baselines.1

Using observational event data to forecast societal events has been extensively studied in data-driven models. Prior work focuses on correlational analysis and ignores the importance of causal relationships behind events. Understanding the causality of events helps one infer future events by pinpointing potential triggers. In light of complex and dynamic social environments, it is difficult to comprehensively analyze the causes of societal events. In this work, we study the causal relationship between topics and events where topics are extracted from event-related documents. These topics represent probability distributions of words. We introduce a method to discover topics that have a causal effect on future events of interest. Next, we propose a causality-enhanced dynamic heterogeneous graph learning framework where topics, documents, and words are represented as nodes with changing edges. To handle the temporal dependencies of dynamic graphs, we introduce a temporal information learning module that updates node representations based on their evolving context and heterogeneous semantics. We conduct extensive experiments on four real-world datasets and demonstrate the effectiveness of our method in societal event prediction.

To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes. However, all existing methods in fair representation learning generate a fairness-information trade-off. To achieve different points on the fairness-information plane, one must train different models. In this paper, we first demonstrate that fairness-information trade-offs are fully characterized by rate-distortion trade-offs. Then, we use this key result and propose SoFaiR, a single shot fair representation learning method that generates with one trained model many points on the fairness-information plane. Besides its computational saving, our single-shot approach is, to the extent of our knowledge, the first fair representation learning method that explains what information is affected by changes in the fairness / distortion properties of the representation. Empirically, we find on three datasets that SoFaiR achieves similar fairness information trade-offs as its multi-shot counterparts.

Data-driven societal event forecasting methods exploit relevant historical information to predict future events. These methods rely on historical labeled data and cannot accurately predict events when data are limited or of poor quality. Studying causal effects between events goes beyond correlation analysis and can contribute to a more robust prediction of events. However, incorporating causality analysis in data-driven event forecasting is challenging due to several factors: (i) Events occur in a complex and dynamic social environment. Many unobserved variables, i.e., hidden confounders, affect both potential causes and outcomes. (ii) Given spatiotemporal non-independent and identically distributed (non-IID) data, modeling hidden confounders for accurate causal effect estimation is not trivial. In this work, we introduce a deep learning framework that integrates causal effect estimation into event forecasting. We first study the problem of Individual Treatment Effect (ITE) estimation from observational event data with spatiotemporal attributes and present a novel causal inference model to estimate ITEs. We then incorporate the learned event-related causal information into event prediction as prior knowledge. Two robust learning modules, including a feature reweighting module and an approximate constraint loss, are introduced to enable prior knowledge injection. We evaluate the proposed causal inference model on real-world event datasets and validate the effectiveness of proposed robust learning modules in event prediction by feeding learned causal information into different deep learning methods. Experimental results demonstrate the strengths of the proposed causal inference model for ITE estimation in societal events and showcase the beneficial properties of robust learning modules in societal event forecasting.

Graphs (or networks) are ubiquitous representation in life sciences and medicine, from molecular interactions maps, signaling transduction pathways, to graphs of scientific knowledge and patient- disease-intervention relationships derived from population studies and/or real-world data, such as electronic health records and insurance claims. Recent advance in graph machine learning (ML) approaches such as graph neural networks (GNNs) has transformed a diverse set of problems relying on biomedical networks that traditionally depend on descriptive topological data analyses. Small- and macro- molecules that were not modeled as graphs also saw a bloom in GNN-based algorithms improving the state-of-the-art performance for learning their properties. Comparing to graph ML applications from other domains, life sciences offer many unique problems and nuances ranging from graph construction to graph- level, and bi-graph-level supervision tasks.

Higher education institutions increasingly rely on machine learning models. However, a growing body of evidence shows that these algorithms may not serve underprivileged communities well and at times discriminate against them. This is all the more concerning in education as negative outcomes have long-term implications. We propose a systematic process for framing, detecting, documenting, and reporting unfairness risks. The systematic approach’s outcomes are merged into a framework named FairEd, which would help decision-makers to understand unfairness risks along the environmental and analytical fairness dimension. The tool allows to decide (i) whether the dataset contains risks of unfairness; (ii) how the models could perform along many fairness dimensions; (iii) whether potentially unfair outcomes can be mitigated without degrading performance. The systematic approach is applied to a Chilean University case study, where a predicting student dropout model is aimed to build. First, we capture the nuances of the Chilean context where unfairness emerges along income lines and demographic groups. Second, we highlight the benefit of reporting unfairness risks along a diverse set of metrics to shed light on potential discrimination. Third, we find that measuring the cost of fairness is an important quantity to report on when doing the model selection.

Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to map data into a compressed binary representation independent of sensitive attributes. We show that in an information bottleneck framework, a parsimonious representation should filter out information related to sensitive attributes if they are provided directly to the decoder. Empirical results show that the method achieves state-of-the-art accuracy-fairness trade-off and that explicit control of the entropy of the representation bit stream allows the user to move smoothly and simultaneously along both rate-distortion and rate-fairness curves.

This paper explores the statistical properties of fair representation learning, a pre-processing method that preemptively removes the correlations between features and sensitive attributes by mapping features to a fair representation space. We show that the demographic parity of a representation can be certified from a finite sample if and only if the mapping guarantees that the chi-squared mutual information between features and representations is finite for distributions of the features. Empirically, we find that smoothing representations with an additive Gaussian white noise provides generalization guarantees of fairness certificates, which improves upon existing fair representation learning approaches.

Data-driven assistive wearable technologies are promising to support young adults with neurodiversity in inclusive education. Existing datasets focus on wearable sensor data of various activities from neurotypical people. However, no dataset exists including learning-related activity data from individuals with neurodiversity. The contributions of this paper include (1) WLA4ND, a dataset of learning activities performed by eight young adults with neurodiversity collected from smartwatch sensors. The activities are common learning tasks, including reading, writing, typing, answering follow-up questions, and off-task. (2) Evaluation of classification on WLA4ND with five activity recognition models, including conventional and deep learning methods. The Convolutional Recurrent Neural Network (CRNN) model achieved a balanced accuracy of 92.2% for user-dependent evaluations, while Federated Multi-Task Hierarchical Attention Model (FATHOM) achieved 91.8% for user-independent evaluations. This evaluation demonstrates that existing activity recognition technologies can be applied to neurodiverse populations. Also, WLA4ND can be used by researchers as a complement for activity recognition, automatic labeling, and next-generation assistive wearable applications.

Federated learning (FL) involves multiple distributed devices jointly training a shared model without any of the participants having to reveal their local data to a centralized server. Most of previous FL approaches assume that data on devices are fixed and stationary during the training process. However, this assumption is unrealistic because these devices usually have varying sampling rates and different system configurations. In addition, the underlying distribution of the device data can change dynamically over time, which is known as concept drift. Concept drift makes the learning process complicated because of the inconsistency between existing and upcoming data. Traditional concept drift handling techniques such as chunk based and ensemble learning-based methods are not suitable in the federated learning frameworks due to the heterogeneity of local devices. We propose a novel approach, FedConD, to detect and deal with the concept drift on local devices and minimize the effect on the performance of models in asynchronous FL. The drift detection strategy is based on an adaptive mechanism which uses the historical performance of the local models. The drift adaptation is realized by adjusting the regularization parameter of objective function on each local device. Additionally, we design a communication strategy on the server side to select local updates in a prudent fashion and speed up model convergence. Experimental evaluations on three evolving data streams and two image datasets show that FedConD detects and handles concept drift, and also reduces the overall communication cost compared to other baseline methods.

In this work, we present an ensemble based sign video recognition method. Our proposed method uses different input representations – such as RGB video and body key-points or pose data – to model sign videos in a multi-modal manner. We represent an input sign video in two ways: the dense frame and the sparse frame inputs. The dense input uses 3D Convolutional Neural Network (CNN) on a 64 frame input window and Long Short Term Memory (LSTM) Network on 32 frame pose input. The sparse input picks 5 representative frames from a sign video, and utilizes CNN and Graph Convolutional Network (GCN) based modeling. These representative frames for a video are selected using pose confidences that are obtained from an off-the-shelf pose estimation model. Our experimental results show that, while the dense 3D CNN model achieves best performance as a single classifier, the GCN based sparse model provides extra recognition capacity. More specifically, the sparse modeling source, when added with the dense modeling in an ensemble manner, can disambiguate similar looking sign classes. Our proposed multi-source ensemble method outperforms several state-of-the-art methods on AUTSL Turkish sign language benchmark dataset.

Deep learning models have been studied to forecast human events using vast volumes of data, yet they still cannot be trusted in certain applications such as healthcare and disaster assistance due to the lack of interpretability. Providing explanations for event predictions not only helps practitioners understand the underlying mechanism of prediction behavior but also enhances the robustness of event analysis. Improving the transparency of event prediction models is challenging given the following factors: (i) multilevel features exist in event data which creates a challenge to cross-utilize different levels of data; (ii) features across different levels and time steps are heterogeneous and dependent; and (iii) static model-level interpretations cannot be easily adapted to event forecasting given the dynamic and temporal characteristics of the data. Recent interpretation methods have proven their capabilities in tasks that deal with graph-structured or relational data. In this paper, we present a Contextualized Multilevel Feature learning framework, CMF, for interpretable temporal event prediction. It consists of a predictor for forecasting events of interest and an explanation module for interpreting model predictions. We design a new context-based feature fusion method to integrate multiple levels of heterogeneous features. We also introduce a temporal explanation module to determine sequences of text and subgraphs that have crucial roles in a prediction. We conduct extensive experiments on several real-world datasets of political and epidemic events. We demonstrate that the proposed method is competitive compared with the state-of-the-art models while possessing favorable interpretation capabilities.

We present a Research-to-Practice paper where we used role-play case studies to improve student understanding of the ethics of algorithms. As the use of algorithmic decision-making continues to grow across areas of society, there is a need to prepare future technology workforce for ethical thinking related. Our work was informed by the situated learning paradigm, and our goal was to improve perspectival thinking among students. Recognizing an issue from multiple perspectives and taking on different perspectives to examine it leads to increased understanding. Drawing on this work, we created and implemented a role-play case study in an undergraduate computing data mining course. The role-play case study focused on the use of algorithms for facial recognition. Data were collected from pre-and post-discussion assignments, and a student survey. Thirty-one students enrolled in the course and completed the ethics module. The data collected in the assignments focused on student's recognition of ethical dilemmas, the change in student's perspective on the case due to creating a collaborative consensus and understanding the complexity of algorithmic decision making. To formally analyze the data, we created a coding schema drawing on the literature and preliminary qualitative analysis of our data. The data were independently coded by multiple coders. The findings indicate that through their participation in collaborative role-play scenarios, students were able to recognize a wide range of issues and offer potential solutions. We discuss the implications of the work. Curriculum material created as part of this work is available as an open education resource.

Federated learning (FL) involves training a model over massive distributed devices, while keeping the training data localized and private. This form of collaborative learning exposes new tradeoffs among model convergence speed, model accuracy, balance across clients, and communication cost, with new challenges including: (1) straggler problem---where clients lag due to data or (computing and network) resource heterogeneity, and (2) communication bottleneck---where a large number of clients communicate their local updates to a central server and bottleneck the server. Many existing FL methods focus on optimizing along only one single dimension of the tradeoff space. Existing solutions use asynchronous model updating or tiering-based, synchronous mechanisms to tackle the straggler problem. However, asynchronous methods can easily create a communication bottleneck, while tiering may introduce biases that favor faster tiers with shorter response latencies.

Gestures in American Sign Language (ASL) are characterized by fast, highly articulate motion of upper body, including arm movements with complex hand shapes and facial expressions. In this work, we propose a new method for word-level sign recognition from American Sign Language (ASL) using video. Our method uses both motion and hand shape cues while being robust to variations of execution. We exploit the knowledge of the body pose, estimated from an off-the-shelf pose estimator. Using the pose as a guide, we pool spatio-temporal feature maps from different layers of a 3D convolutional neural network. We train separate classifiers using pose guided pooled features from different resolutions and fuse their prediction scores during test time. This leads to a significant improvement in performance on the WLASL benchmark dataset [25]. The proposed approach achieves 10%, 12%, 9.5% and 6.5% performance gain on WLASL100, WLASL300, WLASL1000, WLASL2000 subsets respectively. To demonstrate the robustness of the pose guided pooling and proposed fusion mechanism, we also evaluate our method by fine tuning the model on another dataset. This yields 10% performance improvement for the proposed method using only 0.4% training data during fine tuning stage.

In today's digital world, rapid technological advancements continue to lessen the burden of tasks for individuals. Among these tasks is communication across perceived language barriers. Indeed, increased attention has been drawn to American Sign Language (ASL) recognition in recent years. Camera-based and motion detection-based methods have been researched extensively; however, there remains a divide in communication between ASL users and non-users. Therefore, this research team proposes the use of a novel wireless sensor (Frequency-Modulated Continuous-Wave Radar) to help bridge the gap in communication. In short, this device sends out signals that detect the user's body positioning in space. These signals then reflect off the body and back to the sensor, developing thousands of cloud points per second, indicating where the body is positioned in space. These cloud points can then be examined for movement over multiple consecutive time frames using a cell division algorithm, ultimately showing how the body moves through space as it completes a single gesture or sentence. At the end of the project, 95% accuracy was achieved in one-object prediction as well as 80% accuracy on cross-object prediction with 30% other objects' data introduced on 19 commonly used gestures. There are 30 samples for each gesture per person from three persons.

During the onset of a natural or man-made crisis event, public often share relevant information for emergency services on social web platforms such as Twitter. However, filtering such relevant data in real-time at scale using social media mining is challenging due to the short noisy text, sparse availability of relevant data, and also, practical limitations in collecting large labeled data during an ongoing event. In this paper, we hypothesize that unsupervised domain adaptation through multi-task learning can be a useful framework to leverage data from past crisis events for training efficient information filtering models during the sudden onset of a new crisis. We present a novel method to classify relevant social posts during an ongoing crisis without seeing any new data from this event (fully unsupervised domain adaptation). Specifically, we construct a customized multi-task architecture with a multi-domain discriminator for crisis analytics: multi-task domain adversarial attention network (MT-DAAN). This model consists of dedicated attention layers for each task to provide model interpretability; critical for real-word applications. As deep networks struggle with sparse datasets, we show that this can be improved by sharing a base layer for multitask learning and domain adversarial training. The framework is validated with the public datasets of TREC incident streams that provide labeled Twitter posts (tweets) with relevant classes (Priority, Factoid, Sentiment) across 10 different crisis events such as floods and earthquakes. Evaluation of domain adaptation for crisis events is performed by choosing one target event as the test set and training on the rest. Our results show that the multi-task model outperformed its single-task counterpart. For the qualitative evaluation of interpretability, we show that the attention layer can be used as a guide to explain the model predictions and empower emergency services for exploring accountability of the model, by showcasing the words in a tweet that are deemed important in the classification process. Finally, we show a practical implication of our work by providing a use-case for the COVID-19 pandemic.

Federated learning (FL) is a machine learning paradigm where a shared central model is learned across distributed devices while the training data remains on these devices. Federated Averaging (FedAvg) is the leading optimization method for training non-convex models in this setting with a synchronized protocol. However, the assumptions made by FedAvg are not realistic given the heterogeneity of devices. First, the volume and distribution of collected data vary in the training process due to different sampling rates of edge devices. Second, the edge devices themselves also vary in latency and system configurations, such as memory, processor speed, and power requirements. This leads to vastly different computation times. Third, availability issues at edge devices can lead to a lack of contribution from specific edge devices to the federated model. In this paper, we present an Asynchronous Online Federated Learning (ASO-Fed) framework, where the edge devices perform online learning with continuous streaming local data and a central server aggregates model parameters from clients. Our framework updates the central model in an asynchronous manner to tackle the challenges associated with both varying computational loads at heterogeneous edge devices and edge devices that lag behind or dropout. We perform extensive experiments on a benchmark image dataset and three real-world datasets with non-IID streaming data. The results demonstrate ASO-Fed converging fast and maintaining good prediction performance.

Forecasting influenza-like illness (ILI) is of prime importance to epidemiologists and health-care providers. Early prediction of epidemic outbreaks plays a pivotal role in disease intervention and control. Most existing work has either limited long-term prediction performance or fails to capture spatio-temporal dependencies in data. In this paper, we design a cross-location attention based graph neural network (Cola-GNN) for learning time series embeddings in long-term ILI predictions. We propose a graph message passing framework to combine graph structures (e.g., geolocations) and time-series features (e.g., temporal sequences) in a dynamic propagation process. We compare the proposed method with state-of-the-art statistical approaches and deep learning models. We conducted a set of extensive experiments on real-world epidemic-related datasets from the United States and Japan. The proposed method demonstrated strong predictive performance and leads to interpretable results for long-term epidemic predictions.

This work presents an approach for American Sign Language (ASL) gesture recognition from videos. Gestures are comprised of various upper body motions involving hand shapes, motion of both hands with facial expression and head movements. Previous approaches tackled this problem by directly learning 3D convolutional spatio-temporal models from video in a simplified settings with uniform backgrounds. To handle more complex variation in appearance and backgrounds we propose to exploit recent advances in estimation of 2D body pose using Deep Convolutional Neural Networks trained on large corpus of human pose annotations. We use the trajectories of 2D skeletal data estimated from video to train a baseline recursive neural network gesture recognition model. The basic model is further extended using embeddings of hand images obtained from another hand shape recognition model [15] with dynamics modeled by another recursive neural network. The final model learns how to fuse two Long Short Term Model (LSTM) recursive neural network models for skeletal and hand image data. We train and evaluate this model on the GMU-ASL51 dataset of 12 users and 51 ASL gestures [8] demonstrating its superior performance compared to several baseline models.

American Sign Language recognition is a difficult gesture recognition problem, characterized by fast, highly articulate gestures. These are comprised of arm movements with different hand shapes, facial expression and head movements. Among these components, hand shape is the vital, often the most discriminative part of a gesture. In this work, we present an approach for effective learning of hand shape embeddings, which are discriminative for ASL gestures. For hand shape recognition our method uses a mix of manually labelled hand shapes and high confidence predictions to train deep convolutional neural network (CNN). The sequential gesture component is captured by recursive neural network (RNN) trained on the embeddings learned in the first stage. We will demonstrate that higher quality hand shape models can significantly improve the accuracy of final video gesture classification in challenging conditions with variety of speakers, different illumination and significant motion blurr. We compare our model to alternative approaches exploiting different modalities and representations of the data and show improved video gesture recognition accuracy on GMU-ASL51 benchmark dataset.

Data mining algorithms are increasingly used in automated decision making across all walks of daily life. Unfortunately, as reported in several studies these algorithms learn bias from data and environment leading to unequitable and unfair solutions. To mitigate bias in machine learning, different formalizations of fairness have been proposed that can be categorized into group fairness and individual fairness. Group fairness requires that different groups should be treated similarly which might be unfair to some individuals within a group. On the other hand, individual fairness requires that similar individuals be treated similarly. However, individual fairness remains understudied due to its reliance on problem-specific similarity metric. We propose a metric-free individual fairness and a cooperative contextual bandits (CCB) algorithm. The CCB algorithm utilizes fairness as a reward and attempts to maximize it. The advantage of treating fairness as a reward is that the fairness criterion does not need to be differentiable. The proposed algorithm is tested on multiple real-world benchmark datasets. The results show the effectiveness of the proposed algorithm at mitigating bias and at achieving both individual and group fairness.

The past decade has been marked by the rapid emergence and proliferation of a myriad of small devices, such as smartphones and wearables. There is a critical need for analysis of multivariate temporal data obtained from sensors on these devices. Given the heterogeneity of sensor data, individual devices may not have sufficient quality data to learn an effective model. Factors such as skewed/varied data distributions bring more difficulties to the sensor data analytics. In this paper, we propose to leverage multi-task learning with attention mechanism to perform inductive knowledge transfer among related devices and improve generalization performance. We design a novel federated multi-task hierarchical attention model (FATHOM) that jointly trains classification/regression models from multiple distributed devices. The attention mechanism in the proposed model seeks to extract feature representations from inputs and to learn a shared representation across multiple devices to identify key features at each time step. The underlying temporal and nonlinear relationships are modeled using a combination of attention mechanism and long short-term memory (LSTM) networks. The proposed method outperforms a wide range of competitive baselines in both classification and regression settings on three unbalanced real-world datasets. It also allows for the visual characterization of key features learned at the input task level and the global temporal level.

Modeling concurrent events of multiple types and their involved actors from open-source social sensors is an important task for many domains such as health care, disaster relief, and financial analysis. Forecasting events in the future can help human analysts better understand global social dynamics and make quick and accurate decisions. Anticipating participants or actors who may be involved in these activities can also help stakeholders to better respond to unexpected events. However, achieving these goals is challenging due to several factors: (i) it is hard to filter relevant information from large-scale input, (ii) the input data is usually high dimensional, unstructured, and Non-IID (Non-independent and identically distributed) and (iii) associated text features are dynamic and vary over time. Recently, graph neural networks have demonstrated strengths in learning complex and relational data. In this paper, we study a temporal graph learning method with heterogeneous data fusion for predicting concurrent events of multiple types and inferring multiple candidate actors simultaneously. In order to capture temporal information from historical data, we propose Glean, a graph learning framework based on event knowledge graphs to incorporate both relational and word contexts. We present a context-aware embedding fusion module to enrich hidden features for event actors. We conducted extensive experiments on multiple real-world datasets and show that the proposed method is competitive against various state-of-the-art methods for social event prediction and also provides much-need interpretation capabilities.

Over half a million people in the United States use American Sign Language (ASL) as their primary mode of communication. Automatic ASL recognition would enable Deaf and Hard of Hearing (DHH) users to interact with others who are not familiar with ASL as well as voice-controlled digital assistants (e.g., Alexa, Siri, etc.). While ASL recognition has been extensively studied, there is a little attention given to recognition of ASL non-manual body markers. The non-manual markers are typically expressed through head, torso and shoulder movements, and add essential meaning and context to the signed sentences. In this work, we present ExASL, a sentence-level ASL recognition system using millimeter-wave radars. ExASL can recognize manual markers (hand gestures) and non-manual markers (head and torso movements). It utilizes multi-distance clustering to recognize body parts and cluster mmWave point clouds. We then present a multi-view deep learning algorithm that can learn from clustered body part representation for an expressive sentence-level recognition. Our evaluation shows that ExASL can recognize ASL sentences with a word error rate of 0.79%, sentence error rate of 1.25%, and non-manual markers with an accuracy of 83.5%.

MOTIVATION: The human body hosts more microbial organisms than human cells. Analysis of this microbial diversity provides key insight into the role played by these microorganisms on human health. Metagenomics is the collective DNA sequencing of coexisting microbial organisms in an environmental sample or a host. This has several applications in precision medicine, agriculture, environmental science and forensics. State-of-the-art predictive models for phenotype predictions from metagenomic data rely on alignments, assembly, extensive pruning, taxonomic profiling and reference sequence databases. These processes are time consuming and they do not consider novel microbial sequences when aligned with the reference genome, limiting the potential of whole metagenomics. We formulate the problem of predicting human disease from whole-metagenomic data using Multiple Instance Learning (MIL), a popular supervised learning paradigm. Our proposed alignment-free approach provides higher accuracy in prediction by harnessing the capability of deep convolutional neural network (CNN) within a MIL framework and provides interpretability via neural attention mechanism. RESULTS: The MIL formulation combined with the hierarchical feature extraction capability of deep-CNN provides significantly better predictive performance compared to popular existing approaches. The attention mechanism allows for the identification of groups of sequences that are likely to be correlated to diseases providing the much-needed interpretation. Our proposed approach does not rely on alignment, assembly and reference sequence databases; making it fast and scalable for large-scale metagenomic data. We evaluate our method on well-known large-scale metagenomic studies and show that our proposed approach outperforms comparative state-of-the-art methods for disease prediction. AVAILABILITY AND IMPLEMENTATION: https://github.com/mrahma23/IDMIL.

The recent advent of Metagenome Wide Association Studies (MGWAS) provides insight into the role of microbes on human health and disease. However, the studies present several computational challenges. In this paper, we demonstrate a novel, efficient, and effective Multiple Instance Learning (MIL) based computational pipeline to predict patient phenotype from metagenomic data. MIL methods have the advantage that besides predicting the clinical phenotype, we can infer the instance level label or role of microbial sequence reads in the specific disease. Specifically, we use a Bag of Words method, which has been shown to be one of the most effective and efficient MIL methods. This involves assembly of the metagenomic sequence data, clustering of the assembled contigs, extracting features from the contigs, and using an SVM classifier to predict patient labels and identify the most relevant sequence clusters. With the exception of the given labels for the patients, this entire process is de novo (unsupervised). We call our pipeline "CAMIL", which stands for Clustering and Assembly with Multiple Instance Learning. We use multiple state-of-the-art clustering methods for feature extraction, evaluation, and comparison of the performance of our proposed approach for each of these clustering methods. We also present a fast and scalable pre-clustering algorithm as a preprocessing step for our proposed pipeline. Our approach achieves efficiency by partitioning the large number of sequence reads into groups (called canopies) using locality sensitive hashing (LSH). These canopies are then refined by using state-of-the-art sequence clustering algorithms. We use data from a well-known MGWAS study of patients with Type-2 Diabetes and show that our pipeline significantly outperforms the classifier used in that paper, as well as other common MIL methods.

Sensors and internet of things (IoTs) are ubiquitous in our modern day-to-day living. Applications range from smart home devices that control cooking ranges to mobile phones, wearable devices that serve as fitness trackers and personalized coaches. There is a critical need for the analysis of heterogeneous multivariate temporal data obtained from individual sensors. In this work we show that multi-task learning (MTL) is naturally suited for sensor data learning, and propose a novel multi-task learning approach with attention mechanism, M-Att, that jointly trains classification/regression models from multiple related tasks where data on each task is generated from one or more sensors. The temporal and non-linear relationships underlying the captured data are modeled using a combination of both convolution neural network (CNN) and long-short term memory (LSTM) models. And the attention mechanism seeks to learn shared feature representations across multiple tasks for improving the overall generalizability of the machine learning model. We evaluate our proposed method in both classification and regression settings on an activity recognition dataset and environment monitoring dataset. Comparing the proposed approach to other competitive single-task learning and multi-task learning approaches we demonstrate the high performance of our proposed model with promising results.

Voice-controlled personal and home assistants (such as the Amazon Echo and Apple Siri) are becoming increasingly popular for a variety of applications. However, the benefits of these technologies are not readily accessible to Deaf or Hard-of-Hearing (DHH) users. The objective of this study is to develop and evaluate a sign recognition system using multiple modalities that can be used by DHH signers to interact with voice-controlled devices. With the advancement of depth sensors, skeletal data is used for applications like video analysis and activity recognition. Despite having similarity with the well-studied human activity recognition, the use of 3D skeleton data in sign language recognition is rare. This is because unlike activity recognition, sign language is mostly dependent on hand shape pattern. In this work, we investigate the feasibility of using skeletal and RGB video data for sign language recognition using a combination of different deep learning architectures. We validate our results on a large-scale American Sign Language (ASL) dataset of 12 users and 13107 samples across 51 signs. It is named as GMU-ASL51. We collected the dataset over 6 months and it will be publicly released in the hope of spurring further machine learning research towards providing improved accessibility for digital assistants.

Over the past decade low graduation and retention rates has plagued higher education institutions. To assist students in choosing a sequence of courses, choosing majors and successful academic pathways; many institutions provide several on-site academic advising services supported by data driven educational technologies. Accurate performance prediction can serve as the backbone for degree planning software, personalized advising systems and early warning systems that can identify students at-risk of dropping from their field of study. In this work, we present a deep learning based recommender system approach called Neural Collaborative Filtering (NCF) for predicting the grade a student will earn in a course that he/she plans to take in the next-term. Prior grade prediction methods are based on matrix factorization (MF) where students and courses are represented in a latent "knowledge" space. The deep learning inspired approach provides added flexibility in learning the latent spaces in comparison to MF approaches. The proposed approach also incorporates instructor information besides student and course information. Moreover, for proper analysis of the learned model parameters, we assume the embeddings obtained for students, courses and instructors should be non-negative. This non-negative NCF model referred by NCFnn model adds a rectified linear units (ReLU) on the embedding layer of NCF. The experimental results on datasets from George Mason University, a large, public university in the United States, demonstrate that the proposed NCF approaches significantly outperform competitive baselines across different test sets.

Machine learning algorithms are increasingly involved in sensitive decision-making processes with adversarial implications on individuals. This paper presents a new tool, mdfa that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differential fairness. Multi-differential fairness is a guarantee that a black box classifier's outcomes do not leak information on the sensitive attributes of a small group of individuals. We reduce the problem of identifying worst-case violations to matching distributions and predicting where sensitive attributes and classifier's outcomes coincide. We apply mdfa to a recidivism risk assessment classifier widely used in the United States and demonstrate that for individuals with little criminal history, identified African-Americans are three-times more likely to be considered at high risk of violent recidivism than similar non-African-Americans.

Finding nearest neighbors is an important topic that has attracted much attention over the years and has applications in many fields, such as market basket analysis, plagiarism and anomaly detection, community detection, ligand-based virtual screening, etc. As data are easier and easier to collect, finding neighbors has become a potential bottleneck in analysis pipelines. Performing pairwise comparisons given the massive datasets of today is no longer feasible. The high computational complexity of the task has led researchers to develop approximate methods, which find many but not all of the nearest neighbors. Yet, for some types of data, efficient exact solutions have been found by carefully partitioning or filtering the search space in a way that avoids most unnecessary comparisons.

Event forecasting with an aim at modeling contextual information is an important task for applications such as automated analysis generation and resource allocation. Captured contextual information for an event of interest can aid human analysts in understanding the factors associated with that event. However, capturing contextual information within event forecasting is challenging due to several factors: (i) uncertainty of context structure and formulation, (ii) high dimensional features, and (iii) adaptation of features over time. Recently, graph representations have demonstrated success in applications such as traffic forecasting, social influence prediction, and visual question answering systems. In this paper, we study graph representations in modeling social events to identify dynamic properties of event contexts as social indicators. Inspired by graph neural networks, we propose a novel graph convolutional network for predicting future events (e.g., civil unrest movements). We extract and learn graph representations from historical/prior event documents. By employing the hidden word graph features, our proposed model predicts the occurrence of future events and identifies sequences of dynamic graphs as event context. Experimental results on multiple real-world data sets show that the proposed method is competitive against various state-of-the-art methods for social event prediction.

Spatio-temporal societal event forecasting, which has traditionally been prohibitively challenging, is now becoming possible and experiencing rapid growth thanks to the big data from Open Source Indicators (OSI) such as social media, news sources, blogs, economic indicators, and other meta-data sources. Spatio-temporal societal event forecasting and their precursor discovery benefit the society by providing insight into events such as political crises, humanitarian crises, mass violence, riots, mass migrations, disease outbreaks, economic instability, resource shortages, natural disasters, and others. In contrast to traditional event detection that identifies ongoing events, event forecasting focuses on predicting future events yet to happen. Also different from traditional spatio-temporal predictions on numerical indices, spatio-temporal event forecasting needs to leverage the heterogeneous information from OSI to discover the predictive indicators and mappings to future societal events. While studying large scale societal events, policy makers and practitioners aim to identify precursors to such events to help understand causative attributes and ensure accountability. The resulting problems typically require the predictive modeling techniques that can jointly handle semantic, temporal, and spatial information, and require a design of efficient and interpretable algorithms that scale to high-dimensional large real-world datasets.

Currently, college-going students are taking longer to graduate than their parental generations. Further, in the United States, the six-year graduation rate has been 59% for decades. Improving the educational quality by training better-prepared students who can successfully graduate in a timely manner is critical. Accurately predicting students' grades in future courses has attracted much attention as it can help identify at-risk students early so that personalized feedback can be provided to them on time by advisors. Prior research on students' grade prediction include shallow linear models; however, students' learning is a highly complex process that involves the accumulation of knowledge across a sequence of courses that can not be sufficiently modeled by these linear models. In addition to that, prior approaches focus on prediction accuracy without considering prediction uncertainty, which is essential for advising and decision making. In this work, we present two types of Bayesian deep learning models for grade prediction under a course-specific framework: i)Multilayer Perceptron (MLP) and ii) Recurrent Neural Network (RNN). These course-specific models are based on the assumption that prior courses can provide students with knowledge for future courses so that grades of prior courses can be used to predict grades in a future course. The MLP ignores the temporal dynamics of students' knowledge evolution. Hence, we propose RNN for students' performance prediction. To evaluate the performance of the proposed models, we performed extensive experiments on data collected from a large public university. The experimental results show that the proposed models achieve better performance than prior state-of-the-art approaches. Besides more accurate results, Bayesian deep learning models estimate uncertainty associated with the predictions. We explore how uncertainty estimation can be applied towards developing a reliable educational early warning system. In addition to uncertainty, we also develop an approach to explain the prediction results, which is useful for advisors to provide personalized feedback to students.

Classical event encoding and extraction methods rely on fixed dictionaries of keywords and templates or require ground truth labels for phrase/sentences. This hinders widespread application of information encoding approaches to large-scale free form (unstructured) text available on the web. Event encoding can be viewed as a hierarchical task where the coarser level task is event detection, i.e., identification of documents containing a specific event, and where the fine-grained task is one of event encoding, i.e., identifying key phrases, key sentences. Hierarchical models with attention seem like a natural choice for this problem, given their ability to differentially attend to more or less important features when constructing document representations. In this work we present a novel factorized bilinear multi-aspect attention mechanism (FBMA) that attends to different aspects of text while constructing its representation. We find that our approach outperforms state-of-the-art baselines for detecting civil unrest, military action, and non-state actor events from corpora in two different languages.

Mass gatherings often underlie civil disobedience activities and as such run the risk of turning violent, causing damage to both property and people. While civil unrest is a rather common phenomenon, only a small subset of them involve crowds turning violent. How can we distinguish which events are likely to lead to violence? Using articles gathered from thousands of online news sources, we study a two-level multi-instance learning formulation, CrowdForecaster, tailored to forecast violent crowd behavior, specifically violent protests. Using data from five countries in Latin America, we demonstrate not just the predictive utility of our approach, but also its effectiveness in discovering triggering factors, especially in uncovering how and when crowd behavior begets violence.

Higher education institutions in the United States and across the Western world face a critical problem of attrition of college students and this problem is particularly acute within the Science, Technology, Engineering, and Mathematics (STEM) fields. Students are especially vulnerable in the initial years of their academic programs; more than 60% of the dropouts occur in the first two years. Therefore, early identification of at-risk students is crucial for a focused intervention if institutions are to support students towards completion. In this paper we developed and evaluated a survival analysis framework for the early identification of students at the risk of dropping out. We compared the performance of survival analysis approaches to other machine learning approaches including logistic regression, decision trees and boosting. The proposed methods show good performance for early prediction of at-risk students and are also able to predict when a student will dropout with high accuracy. We performed a comparative analysis of nine different majors with varying levels of academic rigor, challenge and student body. This study enables advisors and university administrators to intervene in advance to improve student retention.

Large-scale societal events such as civil unrest movements occur due to a variety of factors including economics, politics, and security. Societal event detection can be modeled as a system of inter-connected locations, where each location is recording a set of time-dependent observations. In order to detect event occurrence and automatically reconstruct the precursors and signals, it is essential to model relationships between the different locations w.r.t. how events evolve over time. However, existing methods for precursor discovery do not capture or exploit spatial and temporal correlations inherent in event occurrences. The absence of such modeling not only creates shortcomings in the quality of inference but also curtails interpretation by human analysts. Furthermore, forecasting is inhibited when training data is sparse. In this paper, we develop a novel multi-task model with dynamic graph constraints within a multi-instance learning framework. Our model tackles the problem of scarce data distribution and reinforces co-occurring location-specific precursors with augmented representations. Through studies on civil unrest movements in numerous countries, we demonstrate the effectiveness of the proposed method for precursor discovery and event forecasting.

The past decade has seen a growth in the development and deployment of educational technologies for assisting college-going students in choosing majors, selecting courses and acquiring feedback based on past academic performance. Grade prediction methods seek to estimate a grade that a student may achieve in a course that she may take in the future (e.g., next term). Accurate and timely prediction of students' academic grades is important for developing effective degree planners and early warning systems, and ultimately improving educational outcomes. Existing grade prediction methods mostly focus on modeling the knowledge components associated with each course and student, and often overlook other factors such as the difficulty of each knowledge component, course instructors, student interest, capabilities and effort. In this paper, we propose additive latent effect models that incorporate these factors to predict the student next-term grades. Specifically, the proposed models take into account four factors: (i) student's academic level, (ii) course instructors, (iii) student global latent factor, and (iv) latent knowledge factors. We compared the new models with several state-of-the-art methods on students of various characteristics (e.g., whether a student transferred in or not). The experimental results demonstrate that the proposed methods significantly outperform the baselines on grade prediction problem. Moreover, we perform a thorough analysis on the importance of different factors and how these factors can practically assist students in course selection, and finally improve their academic performance.

An enduring issue in higher education is student retention and timely graduation. Early-warning and degree planning systems have been identified as a key approach to tackle this problem. Accurately predicting a student's performance can help recommend degree pathways for students and identify students at-risk of dropping from their program of study. Various approaches have been developed for predicting students' next-term grades. Recently, course-specific approaches based on linear regression and matrix factorization have been proposed. To predict a student's grade, course-specific approaches utilize the student's grades from courses taken prior to that course. However, there are a lot of factors other than student's historical grades that influence his/her performance, such as the difficulty of the courses, the quality and pedagogy of the instructor, the academic level of the students when taking the courses and so on. In this paper, we propose a course-specific regression model enriched with features about students, courses and instructors. Our proposed models were evaluated on datasets from two large public universities for academic programs with varying flexibility. The experimental results showed that incorporating content features can boost the performance of the course-specific model. For some degree programs with high flexibility, our experiments showed that predicting the grades with informative content features demonstrated better prediction accuracy.

Most trajectory data are collected with a constant sample rate (e.g. GPS data). However, the variance of velocities can be very large, which causes the non-uniformity of the sample points in trajectory dataset. That is, the trajectory dataset can be very sparse in some parts which cause most existing distance measures to get unexpected results. On the other hand, the dataset can be extremely dense in some other parts which results in unnecessarily high computational complexity. Due to the above phenomenon, choosing an appropriate sample rate becomes a difficult challenge. In order to address the dilemma, we propose a Step-Invariant Trajectory (SIT) representation that can provide a dynamic sample rate to represent any trajectories in a uniform way. The translation takes only linear time. We also propose an effective and scalable distance measure for SIT representation. We evaluate the effectiveness and efficiency of our representation along with its distance measure by performing multiple trajectory classification and clustering experiments. These results show that our distance measures on SIT representation is much more accurate and robust than other representations and distance measures on sparse trajectory datasets. Our approach can also achieve competitive accuracy compared with the state of the art model-based trajectory representations on dense datasets. However, the time required to translate the data to our representation is 2 orders of magnitude faster, on average, than translate to other model-based representations. Furthermore, our representation can also serve as a preprocessing step to provide high quality input to all trajectory learning methods.

In recent years, finding repetitive similar patterns in time series has become a popular problem. These patterns are called time series motifs. Recent studies show that using grammar compression algorithms to find repeating patterns from the symbolized time series holds promise in discovering approximate motifs with variable length. However, grammar compression algorithms are traditionally designed for string compression. Therefore, existing work on grammar induction has not fully utilized much available information that can be used to enhance the performance of the algorithms. In this work, an iterative framework based on grammar induction is proposed. In each iteration, a revision operator called Noise Reduction Operator is applied to revise the symbolized time series string based on the rules returned from a base grammar induction algorithm. In our experiments, we show that the proposed work can find motifs of the same quality, with much faster running time compared to the state-of-the-art variable-length exact motif discovery algorithm in real world time series data.

Hierarchical classification (HC) approaches leverage the hierarchical structure during training and testing of models which helps in the improvement of classification performance and prediction efficiency. However, their performance improvement in comparison to flat approaches may be poor if the hierarchy used for training contains: (i) Inconsistent hierarchical relationships such as parent-child or siblings and (ii) Less cohesive or overlapping classes. Moreover, dynamic changes in the data characteristics over time requires new classes (orphan nodes) to be identified to improve the generalization performance of learned models. In addition, we also need to deal with imbalance data in large-scale problem where large number of classes have a few examples for training, posing statistical challenges. In this paper, we propose an integrated framework to address the aforementioned issues for improving large-scale HC. Our experimental evaluations on various image and text datasets shows improved performance with our proposed framework.

The Self-Paced Learning Increases Retention and Capacity (SPARC) project is responding to the well-documented surge in CS enrollment by creating a self-paced learning environment that blends online learning, automated assessment, collaborative practice, and peer-supported learning. SPARC delivers educational material online, encourages students to practice programming in groups, frees them to learn material at their own pace, and allows them to demonstrate proficiency at any time. This model contrasts with traditional course offerings, which impose a single schedule of due dates and exams for all students. SPARC allows students to complete courses faster or slower at a pace tailored to the individual, thereby allowing universities to teach more students with the same or fewer resources. This paper describes the goals and elements of the SPARC model as applied to CS1. We present results so far and discuss the future of the project.

Recommending personalized content to users is a long-standing challenge to many online services including Facebook, Yahoo, Linkedin and Twitter. Traditional recommendation models such as latent factor models and feature-based models are usually trained for all users and optimize an "average" experience for them, yielding sub-optimal solutions. Although multi-task learning provides an opportunity to learn personalized models per user, learning algorithms are usually tailored to specific models (e.g., generalized linear model, matrix factorization and etc.), creating obstacles for a unified engineering interface, which is important for large Internet companies. In this paper, we present an empirical framework to learn user-specific personal models for content recommendation by utilizing gradient information from a global model. Our proposed method can potentially benefit any model that can be optimized through gradients, offering a lightweight yet generic alternative to conventional multi-task learning algorithms for user personalization. We demonstrate the effectiveness of the proposed framework by incorporating it in three popular machine learning algorithms including logistic regression, gradient boosting decision tree and matrix factorization. Our extensive empirical evaluation shows that the proposed framework can significantly improve the efficiency of personalized recommendation in real-world datasets.

The recent advent of Metagenome-Wide Association Studies (MGWAS) has allowed for increased accuracy in the prediction of patient phenotype (disease), but has also presented big data challenges. Meanwhile, Multiple Instance Learning (MIL) is useful in the domain of bioinformatics because, in addition to classifying patient phenotype, it can also identify individual parts of the microbiome that are indicative of that phenotype, leading to better understanding of the disease. We demonstrate a novel, efficient, and effective MIL-based computational pipeline to predict patient phenotype from MGWAS data. Specifically, we use a Bag of Words method, which has been shown to be one of the most effective and efficient MIL methods. This involves assembly of the metagenomic sequence data, clustering of the assembled contigs, extracting features from the contigs, and using an SVM classifier to predict patient labels and identify the most relevant read clusters. With the exception of the given labels for the patients, this entire process is de novo (unsupervised). We use data from a well-known MGWAS study of patients with Type-2 Diabetes and show that our pipeline significantly outperforms the classifier used in that paper, as well as other common MIL methods. We call our pipeline “CAMIL”, which stands for Clustering and Assembly with Multiple Instance Learning.

Large-scale Hierarchical Classification (HC) involves datasets consisting of thousands of classes and millions of training instances with high-dimensional features posing several big data challenges. Feature selection that aims to select the subset of discriminant features is an effective strategy to deal with large-scale HC problem. It speeds up the training process, reduces the prediction time and minimizes the memory requirements by compressing the total size of learned model weight vectors. Majority of the studies have also shown feature selection to be competent and successful in improving the classification accuracy by removing irrelevant features. In this work, we investigate various filter-based feature selection methods for dimensionality reduction to solve the large-scale HC problem. Our experimental evaluation on text and image datasets with varying distribution of features, classes and instances shows upto 3x order of speed-up on massive datasets and upto 45% less memory requirements for storing the weight vectors of learned model without any significant loss (improvement for some datasets) in the classification accuracy. Source Code: https://cs.gmu.edu/~mlbio/featureselection.

State-of-the-art event encoding approaches rely on sentence or phrase level labeling, which are both time consuming and infeasible to extend to large scale text corpora and emerging domains. Using a multiple instance learning approach, we take advantage of the fact that while labels at the sentence level are difficult to obtain, they are relatively easy to gather at the document level. This enables us to view the problems of event detection and extraction in a unified manner. Using distributed representations of text, we develop a multiple instance formulation that simultaneously classifies news articles and extracts sentences indicative of events without any engineered features. We evaluate our model in its ability to detect news articles about civil unrest events (from Spanish text) across ten Latin American countries and identify the key sentences pertaining to these events. Our model, trained without annotated sentence labels, yields performance that is competitive with selected state-of-the-art models for event detection and sentence identification. Additionally, qualitative experimental results show that the extracted event-related sentences are informative and enhance various downstream applications such as article summarization, visualization, and event encoding.

Large-scale classification of data where classes are structurally organized in a hierarchy is an important area of research. Top-down approaches that exploit the hierarchy during the learning and prediction phase are efficient for large-scale hierarchical classification. However, accuracy of top-down approaches is poor due to error propagation i.e., prediction errors made at higher levels in the hierarchy cannot be corrected at lower levels. One of the main reason behind errors at the higher levels is the presence of inconsistent nodes that are introduced due to the arbitrary process of creating these hierarchies by domain experts. In this paper, we propose two different data-driven approaches (local and global) for hierarchical structure modification that identifies and flattens inconsistent nodes present within the hierarchy. Our extensive empirical evaluation of the proposed approaches on several image and text datasets with varying distribution of features, classes and training instances per class shows improved classification performance over competing hierarchical modification approaches. Specifically, we see an improvement upto 7% in Macro-F1 score with our approach over best TD baseline. SOURCE CODE: http://www.cs.gmu.edu/ mlbio/InconsistentNodeFlattening.

In recent years, finding repetitive similar patterns in time series has become a popular problem. These patterns are called time series motifs. Recent studies show that using grammar compression algorithms to find repeating patterns from the symbolized time series holds promise in discovering approximate motifs with variable length. However, grammar compression algorithms are traditionally designed for string compression. Therefore, existing work on grammar induction has not fully utilized much available information that can be used to enhance the performance of the algorithms. In this work, an iterative framework based on grammar induction is proposed. In each iteration, a revision operator called Noise Reduction Operator is applied to revise the symbolized time series string based on the rules returned from a base grammar induction algorithm. In our experiments, we show that the proposed work can find motifs of the same quality, with much faster running time compared to the state-of-the-art variable-length exact motif discovery algorithm in real world time series data.

Forecasting large-scale societal events like civil unrest movements, disease outbreaks, and elections is an important and challenging problem. From the perspective of human analysts and policy makers, forecasting algorithms must not only make accurate predictions but must also provide supporting evidence, e.g., the causal factors related to the event of interest. We develop a novel multiple instance learning based approach that jointly tackles the problem of identifying evidence-based precursors and forecasts events into the future. Specifically, given a collection of streaming news articles from multiple sources we develop a nested multiple instance learning approach to forecast significant societal events such as protests. Using data from three countries in Latin America, we demonstrate how our approach is able to consistently identify news articles considered as precursors for protests. Our empirical evaluation demonstrates the strengths of our proposed approach in filtering candidate precursors, in forecasting the occurrence of events with a lead time advantage and in accurately predicting the characteristics of civil unrest events.

We present findings from a study examining students' course-taking pathways to graduation and identify the factors regarding course-taking choices that can affect students' performance. The data for the study was collected from two majors within an engineering school at a large public university: computer science (CS) and information technology (IT). Although we look in depth at CS students, we use the other data for a comparative analysis. CS and IT are the most popular and largest majors, respectively, at our institution with almost 2,500 undergraduate students enrolled in them. The results show that there are differences in specific patterns of courses and illustrate relationships between the frequent courses in each semester and the relationships between courses taken in two consecutive semesters. Some major insights from the analysis of trajectory of frequent courses for both groups include: low performers postponed some courses toward the end of the program, and take a collection of courses together that their counterparts do not usually take. This work has direct implications for advising of prospective and current students and can improve programs' curriculum and students' performance. In the next stage of this study we will compare trajectories of students who graduate with those of students who either leave CS and IT or take longer to graduate. This preliminary research is part of a NSF CISE/EHR funded grant project on "BigData and Education".

An enduring issue in higher education is student retention to successful graduation. To further this goal, we develop a system for the task of predicting students' course grades for the next enrollment term in a traditional university setting. Each term, students enroll in a limited number of courses and earn grades in the range A-F for each course. Given historical grade data, our task is to predict the grades for each student in the courses they will enroll in during the next term. With this problem formulation, the next-term student grade prediction problem becomes quite similar to a rating prediction or next-basket recommendation problem. The factorization machine (FM), a general-purpose matrix factorization (MF) algorithm suitable for this task, is leveraged as the state-of-the-art method and compared to a variety of other methods. Our experiments show that FMs achieve the lowest prediction error. Results for both cold-start and non-cold-start prediction demonstrate that FMs can be used to accurately predict in both settings. Finally, we identify limitations observed in FMs and the other models tested and discuss directions for future work. To our knowledge, this is the first study that applies state-of-the-art collaborative filtering algorithms to solve the next-term student grade prediction problem.

With the growth of information organized in hierarchical databases, it is essential to develop automated approaches for classifying data instances (e.g., documents, proteins and images) into hierarchies. Several classification approaches have been developed that exploit the hierarchical structure prevalent within these underlying databases. One commonly used approach is to train local one-versus-rest classifiers for each of the nodes within the hierarchy and then make a prediction using a combination of these several trained classifiers. In this paper, we develop a hierarchical classification approach that utilizes a rank-based loss function to differentiate between the examples from different nodes across the hierarchies. The intuition behind our approach is that it allows for the training examples to have an ordering based on their class membership within the hierarchy. We also add regularization constraints that force the learned weight vectors associated with the parent and children nodes within the hierarchy to be similar to each other. To further improve the model performance, we extend our formulation to include a hierarchy based cost-sensitive loss during training. To ensure the scalability of our approach to datasets with large number of classes, instances and feature space, we implemented a distributed map-reduce based algorithm for training the different per-node classifiers. Our empirical results on a diverse set of image and text hierarchical databases shows an improved performance with the use of rank-based models in comparison to other baseline approaches.

Identifying the concepts covered in a university course based on a high level description is a necessary step in the evaluation of a university's program of study. To this end, data describing university courses is readily available on the Internet in vast quantities. However, understanding natural language course descriptions requires manual inspection and, often, implicit knowledge of the subject area. Additionally, a holistic approach to curricular evaluation involves analysis of the prerequisite structure within a department, specifically the conceptual overlap between courses in a prerequisite chain. In this work we apply existing topic modeling techniques to sets of course descriptions extracted from publicly available university course catalogs. The inferred topic models correspond to concepts taught in the described courses. The inference process is unsupervised and generates topics without the need for manual inspection. We present an application framework for data ingestion and processing, along with a user-facing web-based application for inferred topic presentation. The software provides tools to view the inferred topics for a university's courses, quickly compare departments by their topic composition, and visually analyze conceptual overlap in departmental prerequisite structures. The tool is available online at http://edmine.cs.gmu.edu.

Predicting new links in social networks is an important problem within the network analysis literature. Many existing methods consider a single snapshot of the network as input, neglecting an important aspect of these networks, their temporal evolution over time. In this paper, we incorporate temporal information to solve the link prediction problem. Temporal information comes from the past interactions among the nodes in the network. Using a supervised learning framework, we train a binary classifier which predicts potential new links in the network in the next epoch. Anonymized Facebook data of New Orleans' users over a period of 28 months has been used in this study. Specifically, we train decision tree classifiers and feedforward neural networks to predict new relationships that are going to emerge in the underlying network. Our experiments clearly show that these models when trained with temporal information perform better compared to models trained with no temporal information.

High false alarm rates in Intensive Care Unit (ICU) is a common problem that leads to alarm desensitization -- a phenomenon called alarm fatigue. Alarm fatigue can cause longer response time or missing of important alarms. In this work, we propose a methodology to identify false alarms generated by ICU bedside monitors. The novelty in our approach lies in the extraction of 216 relevant features to capture the characteristics of all alarms, from both arterial blood pressure (ABP) and electrocardiogram (ECG) signals. Our multivariate approach mitigates the imprecision caused by existing heartbeat/peak detection algorithms. Unlike existing methods on ICU false alarm detection, our approach does not require separate techniques for different types of alarms. The experimental results show that our approach can achieve high accuracy on false alarm detection, and can be generalized for different types of alarms.

News has, in this day and age, transformed primarily into a digital format with leading newspapers and news agencies having a significant online presence. The speed at which news reaches the reader notwithstanding, the proliferation of blogs and microblogs to deliver specialized content has become the order of the day. Even highly engaged users tend to disengage with a website when the content they are served is unappealing to them. While recommendation systems have been used to ensure delivery of content to the user in tune with their tastes, these systems face an unprecedented challenge - the transient nature of 'popular' news and users' changing interests. Moreover, the challenge is compounded by the absence of explicit feedback. Most recommendation systems for recommending digital news content rely on inferring user engagement through 'clicks', which is not necessarily an accurate measure as it gives us no explicit information about the degree to which a user is interested in a news article. In this paper, we introduce and study the behavior of temporal and tag-based models for news article recommendation. Our experiments indicate that incorporating temporal and taginformation improves recommendation quality and increases user engagement. We argue through experimental evaluation that the improved performance is due to recommendation of more personalized news content by the tag-based recommendation algorithms as compared to other models that do not explicitly incorporate user-tag information.

Collaborative filtering (CF) based recommender systems identify and recommend interesting items to a given user based on the user's past rating activity. These systems improve their recommendations by identifying user preferences and item related information from external sources, like reviews written by users, or concept tags shared by users about these items. These preferences are often reflected through a multi-criterion rating. In this study, we seek to improve recommender systems by integrating user preferences as side information within standard neighborhood-based and matrix factorization based methods. We assume that a user's choice of tags for an item provides additional information about the user's personal preference and additional features about the item. Since, querying users to provide tags and multi-criteria rating imposes an additional burden on the user base, we propose using collective classification to predict tags for both the users and items. We also investigate the use of active learning approaches integrated within the collective classification framework when tag information (users or items) is limited. Our experimental results on several real world datasets show the advantages of using tag-based information within the recommender systems. We are also able to show the effectiveness of collective classification algorithms in estimating user preferences and item features.

High-throughput experimental techniques provide a wide variety of heterogeneous proteomic data sources. To exploit the information spread across multiple sources for protein function prediction, these data sources are transformed into kernels and then integrated into a composite kernel. Several methods first optimize the weights on these kernels to produce a composite kernel, and then train a classifier on the composite kernel. As such, these approaches result in an optimal composite kernel, but not necessarily in an optimal classifier. On the other hand, some approaches optimize the loss of binary classifiers and learn weights for the different kernels iteratively. For multi-class or multi-label data, these methods have to solve the problem of optimizing weights on these kernels for each of the labels, which are computationally expensive and ignore the correlation among labels. In this paper, we propose a method called Predicting Protein Function using Multiple Kernels (ProMK). ProMK iteratively optimizes the phases of learning optimal weights and reduces the empirical loss of multi-label classifier for each of the labels simultaneously. ProMK can integrate kernels selectively and downgrade the weights on noisy kernels. We investigate the performance of ProMK on several publicly available protein function prediction benchmarks and synthetic datasets. We show that the proposed approach performs better than previously proposed protein function prediction approaches that integrate multiple data sources and multi-label multiple kernel learning methods. The codes of our proposed method are available at https://sites.google.com/site/guoxian85/promk.

Multi-task learning improves generalization performance by learning several related tasks jointly. Several methods have been proposed for multi-task learning in recent years. Many methods make strong assumptions about symmetric task relationships while some are able to utilize externally provided task relationships. However, in many real world tasks the degree of relatedness among tasks is not known a priori. Methods which are able to extract the task relationships and exploit them while simultaneously learning models with good generalization performance can address this limitation. In the current work, we have extended a recently proposed method for learning task relationships using smooth squared loss for regression to classification problems using non-smooth hinge loss due to the demonstrated effectiveness of SVM classifier in single task classification settings. We have also developed an efficient optimization procedure using bundle methods for the proposed multi-task learning formulation. We have validated our method on one simulated and two real world datasets and have compared its performance to competitive baseline single-task and multi-task methods.

Classification problems in which several learning tasks are organized hierarchically pose a special challenge because the hierarchical structure of the problems needs to be considered. Multi-task learning (MTL) provides a framework for dealing with such interrelated learning tasks. When two different hierarchical sources organize similar information, in principle, this combined knowledge can be exploited to further improve classification performance. We have studied this problem in the context of protein structure classification by integrating the learning process for two hierarchical protein structure classification database, SCOP and CATH. Our goal is to accurately predict whether a given protein belongs to a particular class in these hierarchies using only the amino acid sequences. We have utilized the recent developments in multi-task learning to solve the interrelated classification problems. We have also evaluated how the various relationships between tasks affect the classification performance. Our evaluations show that learning schemes in which both the classification databases are used outperform the schemes which utilize only one of them.

The four articles in this special section were presented at the 2013 International Workshop on Data Mining in Bioinformatics (BIOKDD) which was held in conjunction with the ACM Conference on Knowledge Discovery and Data Mining (KDD) in Chicago, IL.

The authors of "Protein Function Prediction Using Multilabel Ensemble Classification" [ibid., vol. 10, no. 4, pp. 1045-1057, July/Aug. 2013] point out a typo that occurred in the Acknowledgments section. The acknowledgment should instead read: "The authors would like to thank the anonymous reviewers and editors for their valuable comments. This paper was partially supported by grants from the US National Science Foundation (NSF) (no. IIS-0905117), the NSF Career Award (no. IIS-1252318), Natural Science Foundation of China (project nos. 61070090, 61003174, 61101234, 61372138), the Natural Science Foundation of Guangdong Province (S2012010009961), Specialized Research Fund for the Doctoral Program of Higher Education (20110172120027), Fundamental Research Funds for the Central Universities of China (project nos. XDJK2010B002, XDJK2013C026, XDJK2013C123, XDJK2014C044), Doctoral Fund of Southwest University (project nos. SWU110063 and SWU113034) and China Scholarship Council (CSC)."

Automated protein function prediction is one of the grand challenges in computational biology. Multi-label learning is widely used to predict functions of proteins. Most of multi-label learning methods make prediction for unlabeled proteins under the assumption that the labeled proteins are completely annotated, i.e., without any missing functions. However, in practice, we may have a subset of the ground-truth functions for a protein, and whether the protein has other functions is unknown. To predict protein functions with incomplete annotations, we propose a Protein Function Prediction method with Weak-label Learning (ProWL) and its variant ProWL-IF. Both ProWL and ProWL-IF can replenish the missing functions of proteins. In addition, ProWL-IF makes use of the knowledge that a protein cannot have certain functions, which can further boost the performance of protein function prediction. Our experimental results on protein-protein interaction networks and gene expression benchmarks validate the effectiveness of both ProWL and ProWL-IF.

Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL considerably outperforms the traditional Single task learning (STL) in terms of prediction accuracy. In this work we develop an MTL based approach for classifying documents that are archived within dual concept hierarchies, namely, DMOZ and Wikipedia. We solve the multi-class classification problem by defining one-versus-rest binary classification tasks for each of the different classes across the two hierarchical datasets. Instead of learning a linear discriminant for each of the different tasks independently, we use a MTL approach with relationships between the different tasks across the datasets established using the non-parametric, lazy, nearest neighbor approach. We also develop and evaluate a transfer learning (TL) approach and compare the MTL (and TL) methods against the standard single task learning and semi-supervised learning approaches. Our empirical results demonstrate the strength of our developed methods that show an improvement especially when there are fewer number of training examples per classification task.

In recent years, many private corporations and government organizations have digitized corpuses of legacy-paper documents. Often, these organizations hope to take advantage of digital representations to transform costly manual tasks associated with paper archives into less-costly computer-assisted tasks. The most common approach toward automated information extraction is through inverted indexing systems that allow fast keyword searches. Keyword-based indexing, however, is ineffective for tasks that require information from higher-level contexts. To allow for more effective information extraction from digital corpuses, we propose combining two common document processing tasks, (i) clustering and (ii) segmentation, into one process to simultaneously segment documents within a corpus and assign each segment to a category. We have developed a generative probabilistic model to accomplish this task, which we call the Joint Segmentation and Clustering (JSC) model. From experiments measuring segmentation and clustering ability, we show that our model can accurately partition documents and assign meaningful categories to each partition. In addition, experiments tracking predictive perplexity show that our JSC model outperforms basic topic modeling approaches in terms of conciseness of the induced representation.

Current bio-technologies allow sequencing of genomes from multiple organisms, that co-exist as communities within ecological environments.This collective genomic process (called metagenomics) has spurred the development of several computational tools for the quantification of abundance, diversity and role of different species within different communities.Unsupervised clustering algorithms (also called binning algorithms) have been developed to group similar metagenome sequences.We have developed an algorithm called MC-MinH that uses the min-wise hashing approach, along with a greedy clustering algorithm to group 16S and whole metagenomic sequences.We represent unequal length sequences using contiguous subsequences or k-mers, and then approximate the computation of pairwise similarity using independent min-wise hashing.The performance of our algorithm is evaluated on several real and simulated metagenomic benchmarks.We demonstrate that our approach is computationally efficient and produces accurate clustering results when evaluated using external ground truth.

High-throughput experimental techniques produce several kinds of heterogeneous proteomic and genomic data sets. To computationally annotate proteins, it is necessary and promising to integrate these heterogeneous data sources. Some methods transform these data sources into different kernels or feature representations. Next, these kernels are linearly (or nonlinearly) combined into a composite kernel. The composite kernel is utilized to develop a predictive model to infer the function of proteins. A protein can have multiple roles and functions (or labels). Therefore, multilabel learning methods are also adapted for protein function prediction. We develop a transductive multilabel classifier (TMC) to predict multiple functions of proteins using several unlabeled proteins. We also propose a method called transductive multilabel ensemble classifier (TMEC) for integrating the different data sources using an ensemble approach. The TMEC trains a graph-based multilabel classifier on each single data source, and then combines the predictions of the individual classifiers. We use a directed birelational graph to capture the relationships between pairs of proteins, between pairs of functions, and between proteins and functions. We evaluate the effectiveness of the TMC and TMEC to predict the functions of proteins on three benchmarks. We show that our approaches perform better than recently proposed protein function prediction methods on composite and multiple kernels. The code, data sets used in this paper and supplemental material are available at https://sites.google.com/site/guoxian85/tmec.

Metagenome sequencing projects attempt to determine the collective DNA of organisms, co-existing as communities across different environments. Computational approaches analyze the large volumes of sequence data obtained from these ecological samples, to provide an understanding of the species diversity, content and abundance. In this work we present a scalable, species diversity estimation algorithm that achieves computational efficiency by use of a locality sensitive hashing algorithm (LSH). Using fixed-length, gapless subsequences, we improve the sensitivity of pairwise sequence comparisons. Using the LSH-based function, we first group similar sequences into bins commonly referred to as operational taxonomic units (OTUs) and then compute several species diversity/richness metrics. The performance of our algorithm is evaluated on synthetic data and eight targeted metagenome samples obtained from the seawater. We compare our results to three state-of-the-art diversity estimation algorithms. We demonstrate the strength of our approach in terms of computational runtime and effective OTU assignments. The source code for LSH-Div is available at the supplementary website under the GNU GPL license. Supplementary material is available at http://www.cs.gmu.edu/~mlbio/LSH-DIV.

Several biological databases organize information in taxonomies/hierarchies. These databases differ in terms of curation process, input data, coverage and annotation errors. SCOP and CATH are examples of two databases that classify proteins hierarchically into structurally related groups based on experimentally determined structures. Given the large number of protein sequences with unavailable structure, there is a need to develop prediction methods to classify protein sequences into structural classes. We have developed a novel classification approach that utilizes the underlying relationships across multiple hierarchical source databases within a multi-task learning (MTL) framework. MTL is used to simultaneously learn multiple related tasks, and has been shown to improve generalization performance. Specifically, we have developed and evaluated an MTL approach for predicting the structural class, as defined by two hierarchical databases, CATH and SCOP, using protein sequence information only. We define one task per node of the hierarchies and formulate the MTL problem as a combination of these binary classification tasks. Our experimental evaluation demonstrates that the MTL approach that integrates both the hierarchies outperforms the base-line approach that trains independent models per task, as well as a MTL approach that integrates tasks across a single hierarchical database. We also performed extensive experiments that evaluate different regularization penalties and incorporate different task relationships that achieve superior classification performance.

Multi-label learning in graph-based relational data has gained popularity in recent years due to the increasingly complex structures of real world applications. Collective Classification deals with the simultaneous classification of neighboring instances in relational data, until a convergence criterion is reached. The rationale behind collective classification stems from the fact that an entity in a network (or relational data) is most likely influenced by the neighboring entities, and can be classified accordingly, based on the class assignment of the neighbors. Although extensive work has been done on collective classification of single labeled data, the domain of multi-labeled relational data has not been sufficiently explored. In this paper, we propose a neighborhood ranking method for multi-label classification, which can be further used in the Multi-label Collective Classification framework. We test our methods on real world datasets and also discuss the relevance of our approach for other multi-labeled relational data. Our experimental results show that the use of ranking in neighborhood selection for collective classification improves the performance of the classifier.

Advances in biotechnology have made available multitudes of heterogeneous proteomic and genomic data. Integrating these heterogeneous data sources, to automatically infer the function of proteins, is a fundamental challenge in computational biology. Several approaches represent each data source with a kernel (similarity) function. The resulting kernels are then integrated to determine a composite kernel, which is used for developing a function prediction model. Proteins are also found to have multiple roles and functions. As such, several approaches cast the protein function prediction problem within a multi-label learning framework. In our work we develop an approach that takes advantage of several unlabeled proteins, along with multiple data sources and multiple functions of proteins. We develop a graph-based transductive multi-label classifier (TMC) that is evaluated on a composite kernel, and also propose a method for data integration using the ensemble framework, called transductive multi-label ensemble classifier (TMEC). The TMEC approach trains a graph-based multi-label classifier for each individual kernel, and then combines the predictions of the individual models. Our contribution is the use of a bi-relational directed graph that captures relationships between pairs of proteins, between pairs of functions, and between proteins and functions. We evaluate the ability of TMC and TMEC to predict the functions of proteins by using two yeast datasets. We show that our approach performs better than recently proposed protein function prediction methods on composite and multiple kernels.

The Profile Hidden Markov Model (PHMM) is commonly used to represent biological sequences. We present a method for transforming the Profile HMM into an equivalent standard HMM where each transition is associated with a single emission. Using this transformation, we develop a beam method, which includes a novel variational adaptation of the infinite-HMM beam sampling technique, to create a fast inference algorithm. We evaluate our algorithm on both synthetic data and protein sequence datasets, showing that our beam method can lead to considerable improvements in runtime while maintaining the model's ability to concisely represent sequences.

The new generation of genomic technologies have allowed researchers to determine the collective DNA of organisms (e.g., microbes) co-existing as communities across the ecosystem (e.g., within the human host). There is a need for the computational approaches to analyze and annotate the large volumes of available sequence data from such microbial communities (metagenomes). In this paper, we developed an efficient and accurate metagenome clustering approach that uses the locality sensitive hashing (LSH) technique to approximate the computational complexity associated with comparing sequences. We introduce the use of fixed-length, gapless subsequences for improving the sensitivity of the LSH-based similarity function. We evaluate the performance of our algorithm on two metagenome datasets associated with microbes existing across different human skin locations. Our empirical results show the strength of the developed approach in comparison to three state-of-the-art sequence clustering algorithms with regards to computational efficiency and clustering quality. We also demonstrate practical significance for the developed clustering algorithm, to compare bacterial diversity and structure across different skin locations.

Social networks and discussion boards have become a significant outlet where people communicate and express their opinion freely. Although the social networks themselves are usually well-provisioned, the participating users frequently point to external links to substantiate their discussions. Unfortunately, the sudden heavy traffic load imposed on the external, linked web sites causes them to become unresponsive leading to the "Flash Crowds" effect. In this paper, we quantify the prevalence of flash crowd events for a popular social discussion board (Digg). We measured the response times of 1289 unique popular websites. We were able to verify that 89% of the popular URLs suffered variations in their response times. By analyzing the content and structure of the social discussions, we were able to forecast accurately for 86% of the popular web sites within 5 minutes of their submission and 95% of the sites when more (5 hours) of social content became available. Our work indicates that we can effectively leverage social activity to forecast network events that will be otherwise infeasible to anticipate.

Advances in sequencing technologies have revolutionized the field of genomics by providing cost effective and high throughput solutions. In this paper, we develop a parallel sequence assembler implemented on general purpose graphic processor units (GPUs). Our work was largely motivated by a growing need in the genomic community for sequence assemblers and increasing use of GPUs for general purpose computing applications. We investigated the implementation challenges, and possible solutions for a data parallel approach for sequence assembly. We implemented an Eulerian-based sequence assembler (GPU-Euler) on the nVidia GPUs using the CUDA programming interface. GPU-Euler was benchmarked on three bacterial genomes using input reads representing the new generation of sequencing approaches. Our empirical evaluation showed that GPU-Euler produced lower run times, and comparable performance in terms of contig length statistics to other serial assemblers. We were able to demonstrate the promise of using GPUs for genome assembly, a computationally intensive task.

Sequence classification is central to many practical problems within machine learning. Distances metrics between arbitrary pairs of sequences can be hard to define because sequences can vary in length and the information contained in the order of sequence elements is lost when standard metrics such as Euclidean distance are applied. We present a scheme that employs a Hidden Markov Model variant to produce a set of fixed-length description vectors from a set of sequences. We then define three inference algorithms, a Baum-Welch variant, a Gibbs Sampling algorithm, and a variational algorithm, to infer model parameters. Finally, we show experimentally that the fixed length representation produced by these inference methods is useful for classifying sequences of amino acids into structural classes.

Assembling short reads obtained from community samples using next-generation sequencing technologies is challenging due to several reasons. In this study we assess the performance of a state-of-the-art Eulerian-path based assembler on a series of simulated dataset with varying complexities. We evaluate the feasibility of metagenomic assembly with reads restricted to length 36 base pairs, obtained from the Solexa/Illumina platform. We developed a pipeline to evaluate the quality of assembly based on contig length statistics and accuracy. We studied the effect of overlap parameters used for the metagenomic assembly and developed a clustering solution to pool the contigs obtained from different runs of the assembly algorithm which allowed us to obtain longer contigs from different runs. We also computed an entropy/impurity metric to assess the degree of chimericity in the assembled contigs. We also compared the metagenomic assemblies to the best possible solution that could be obtained by assembling individual source genomes. Our results show that accuracy was better than expected for the metagenomic samples with a few dominant organisms and was especially poor in samples containing many closely related strains.

BACKGROUND: Over the last decade several prediction methods have been developed for determining the structural and functional properties of individual protein residues using sequence and sequence-derived information. Most of these methods are based on support vector machines as they provide accurate and generalizable prediction models. RESULTS: We present a general purpose protein residue annotation toolkit (svmPRAT) to allow biologists to formulate residue-wise prediction problems. svmPRAT formulates the annotation problem as a classification or regression problem using support vector machines. One of the key features of svmPRAT is its ease of use in incorporating any user-provided information in the form of feature matrices. For every residue svmPRAT captures local information around the reside to create fixed length feature vectors. svmPRAT implements accurate and fast kernel functions, and also introduces a flexible window-based encoding scheme that accurately captures signals and pattern for training effective predictive models. CONCLUSIONS: In this work we evaluate svmPRAT on several classification and regression problems including disorder prediction, residue-wise contact order estimation, DNA-binding site prediction, and local structure alphabet prediction. svmPRAT has also been used for the development of state-of-the-art transmembrane helix prediction method called TOPTMH, and secondary structure prediction method called YASSPP. This toolkit developed provides practitioners an efficient and easy-to-use tool for a wide variety of annotation problems. AVAILABILITY: http://www.cs.gmu.edu/~mlbio/svmprat.

We develop a parallel algorithm for a widely used whole genome alignment method called LAGAN. We use the MPI-based protocol to develop parallel solutions for two phases of the algorithm which take up a significant portion of the total runtime, and also have a high memory requirement. The serial LAGAN program uses CHAOS to quickly determine initial anchor or seeds, which are extended using a sparse dynamic programming based longest-increasing subsequence method. Our work involves parallelizing the CHAOS and LIS phases of the algorithm using a one-dimensional block cyclic partitioning of the computation. This leads to development of an efficient algorithm that utilizes the processors in a balanced way. We also ensure minimum time spent in communication or transfer of information across processors.We also report experimental evaluation of our parallel implementation using pairs of human contigs of varying lengths. We discuss and illustrate the challenges faced in parallelizing a sparse dynamic programming formulation as in this work, and show equivalent to theoretical speedups for our parallelized phases of the LAGAN algorithm.

MOTIVATION: Protein sequence alignment plays a critical role in computational biology as it is an integral part in many analysis tasks designed to solve problems in comparative genomics, structure and function prediction, and homology modeling. METHODS: We have developed novel sequence alignment algorithms that compute the alignment between a pair of sequences based on short fixed- or variable-length high-scoring subsequences. Our algorithms build the alignments by repeatedly selecting the highest scoring pairs of subsequences and using them to construct small portions of the final alignment. We utilize PSI-BLAST generated sequence profiles and employ a profile-to-profile scoring scheme derived from PICASSO. RESULTS: We evaluated the performance of the computed alignments on two recently published benchmark datasets and compared them against the alignments computed by existing state-of-the-art dynamic programming-based profile-to-profile local and global sequence alignment algorithms. Our results show that the new algorithms achieve alignments that are comparable with or better than those achieved by existing algorithms. Moreover, our results also showed that these algorithms can be used to provide better information as to which of the aligned positions are more reliable--a critical piece of information for comparative modeling applications.

BACKGROUND: Protein remote homology detection and fold recognition are central problems in computational biology. Supervised learning algorithms based on support vector machines are currently one of the most effective methods for solving these problems. These methods are primarily used to solve binary classification problems and they have not been extensively used to solve the more general multiclass remote homology prediction and fold recognition problems. RESULTS: We present a comprehensive evaluation of a number of methods for building SVM-based multiclass classification schemes in the context of the SCOP protein classification. These methods include schemes that directly build an SVM-based multiclass model, schemes that employ a second-level learning approach to combine the predictions generated by a set of binary SVM-based classifiers, and schemes that build and combine binary classifiers for various levels of the SCOP hierarchy beyond those defining the target classes. CONCLUSION: Analyzing the performance achieved by the different approaches on four different datasets we show that most of the proposed multiclass SVM-based classification approaches are quite effective in solving the remote homology prediction and fold recognition problems and that the schemes that use predictions from binary models constructed for ancestral categories within the SCOP hierarchy tend to not only lead to lower error rates but also reduce the number of errors in which a superfamily is assigned to an entirely different fold and a fold is predicted as being from a different SCOP class. Our results also show that the limited size of the training data makes it hard to learn complex second-level models, and that models of moderate complexity lead to consistently better results.

MOTIVATION: Protein remote homology detection is a central problem in computational biology. Supervised learning algorithms based on support vector machines are currently one of the most effective methods for remote homology detection. The performance of these methods depends on how the protein sequences are modeled and on the method used to compute the kernel function between them. RESULTS: We introduce two classes of kernel functions that are constructed by combining sequence profiles with new and existing approaches for determining the similarity between pairs of protein sequences. These kernels are constructed directly from these explicit protein similarity measures and employ effective profile-to-profile scoring schemes for measuring the similarity between pairs of proteins. Experiments with remote homology detection and fold recognition problems show that these kernels are capable of producing results that are substantially better than those produced by all of the existing state-of-the-art SVM-based methods. In addition, the experiments show that these kernels, even when used in the absence of profiles, produce results that are better than those produced by existing non-profile-based schemes. AVAILABILITY: The programs for computing the various kernel functions are available on request from the authors.