Author name cluster

Mononito Goswami

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

2 author rows

ICML Conference 2025 Conference Paper

Exploring Representations and Interventions in Time Series Foundation Models

Michal Wilinski
Mononito Goswami
Willa Potosnak
Nina Zukowska
Artur Dubrawski

Time series foundation models (TSFMs) promise to be powerful tools for a wide range of applications. However, their internal representations and learned concepts are still not well understood. In this study, we investigate the structure and redundancy of representations across various TSFMs, examining the self-similarity of model layers within and across different model sizes. This analysis reveals block-like redundancy in the representations, which can be utilized for informed pruning to improve inference speed and efficiency. We also explore the concepts learned by these models, such as periodicity and trends. We demonstrate how conceptual priors can be derived from TSFM representations and leveraged to steer its outputs toward concept-informed predictions. Our work bridges representational analysis from language and vision models to TSFMs, offering new methods for building more computationally efficient and transparent TSFMs.

Details

AAAI Conference 2024 Short Paper

JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract)

Yifu Cai
Arvind Srinivasan
Mononito Goswami
Arjun Choudhry
Artur Dubrawski

Time-series and text data are prevalent in healthcare and frequently co-exist, yet they are typically modeled in isolation. Even studies that jointly model time-series and text, do so by converting time-series to images or graphs. We hypothesize that explicitly modeling time-series jointly with text can improve tasks such as summarization and question answering for time-series data, which have received little attention so far. To address this gap, we introduce JoLT to jointly learn desired representations from pre-trained time-series and text models. JoLT utilizes a Querying Transformer (Q-Former) to align the time-series and text representations. Our experiments on a large real-world electrocardiography dataset for medical time-series summarization show that JoLT outperforms state-of-the-art image captioning approaches.

PDF Details DOI

ICML Conference 2024 Conference Paper

MOMENT: A Family of Open Time-series Foundation Models

Mononito Goswami
Konrad Szafer
Arjun Choudhry
Yifu Cai
Shuo Li
Artur Dubrawski

We introduce MOMENT, a family of open-source foundation models for general-purpose time series analysis. Pre-training large models on time series data is challenging due to (1) the absence of a large and cohesive public time series repository, and (2) diverse time series characteristics which make multi-dataset training onerous. Additionally, (3) experimental benchmarks to evaluate these models, especially in scenarios with limited resources, time, and supervision, are still in their nascent stages. To address these challenges, we compile a large and diverse collection of public time series, called the Time series Pile, and systematically tackle time series-specific challenges to unlock large-scale multi-dataset pre-training. Finally, we build on recent work to design a benchmark to evaluate time series foundation models on diverse tasks and datasets in limited supervision settings. Experiments on this benchmark demonstrate the effectiveness of our pre-trained models with minimal data and task-specific fine-tuning. Finally, we present several interesting empirical observations about large pre-trained time series models. Pre-trained models (AutonLab/MOMENT-1-large) and Time Series Pile (AutonLab/Timeseries-PILE) are available on Huggingface.

Details

AAAI Conference 2024 Short Paper

PICSR: Prototype-Informed Cross-Silo Router for Federated Learning (Student Abstract)

Eric Enouen
Sebastian Caldas
Mononito Goswami
Artur Dubrawski

Federated Learning is an effective approach for learning from data distributed across multiple institutions. While most existing studies are aimed at improving predictive accuracy of models, little work has been done to explain knowledge differences between institutions and the benefits of collaboration. Understanding these differences is critical in cross-silo federated learning domains, e.g., in healthcare or banking, where each institution or silo has a different underlying distribution and stakeholders want to understand how their institution compares to their partners. We introduce Prototype-Informed Cross-Silo Router (PICSR) which utilizes a mixture of experts approach to combine local models derived from multiple silos. Furthermore, by computing data similarity to prototypical samples from each silo, we are able to ground the router’s predictions in the underlying dataset distributions. Experiments on a real-world heart disease prediction dataset show that PICSR retains high performance while enabling further explanations on the differences among institutions compared to a single black-box model.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

AQuA: A Benchmarking Tool for Label Quality Assessment

Mononito Goswami
Vedant Sanil
Arjun Choudhry
Arvind Srinivasan
Chalisa Udompanyawit
Artur Dubrawski

Machine learning (ML) models are only as good as the data they are trained on. But recent studies have found datasets widely used to train and evaluate ML models, e. g. ImageNet, to have pervasive labeling errors. Erroneous labels on the train set hurt ML models' ability to generalize, and they impact evaluation and model selection using the test set. Consequently, learning in the presence of labeling errors is an active area of research, yet this field lacks a comprehensive benchmark to evaluate these methods. Most of these methods are evaluated on a few computer vision datasets with significant variance in the experimental protocols. With such a large pool of methods and inconsistent evaluation, it is also unclear how ML practitioners can choose the right models to assess label quality in their data. To this end, we propose a benchmarking environment AQuA to rigorously evaluate methods that enable machine learning in the presence of label noise. We also introduce a design space to delineate concrete design choices of label error detection models. We hope that our proposed design space and benchmark enable practitioners to choose the right tools to improve their label quality and that our benchmark enables objective and rigorous evaluation of machine learning tools facing mislabeled data.

PDF Details

ICLR Conference 2023 Conference Paper

Unsupervised Model Selection for Time Series Anomaly Detection

Mononito Goswami
Cristian I. Challu
Laurent Callot
Lenon Minorics
Andrey Kan

Anomaly detection in time-series has a wide range of practical applications. While numerous anomaly detection methods have been proposed in the literature, a recent survey concluded that no single method is the most accurate across various datasets. To make matters worse, anomaly labels are scarce and rarely available in practice. The practical problem of selecting the most accurate model for a given dataset without labels has received little attention in the literature. This paper answers this question \textit{i.e.} Given an unlabeled dataset and a set of candidate anomaly detectors, how can we select the most accurate model? To this end, we identify three classes of surrogate (unsupervised) metrics, namely, \textit{prediction error}, \textit{model centrality}, and \textit{performance on injected synthetic anomalies}, and show that some metrics are highly correlated with standard supervised anomaly detection performance metrics such as the $F_1$ score, but to varying degrees. We formulate metric combination with multiple imperfect surrogate metrics as a robust rank aggregation problem. We then provide theoretical justification behind the proposed approach. Large-scale experiments on multiple real-world datasets demonstrate that our proposed unsupervised approach is as effective as selecting the most accurate model based on partially labeled data.

Details

AAAI Conference 2020 Short Paper

A Multi-Task Approach to Open Domain Suggestion Mining (Student Abstract)

Minni Jain
Maitree Leekha
Mononito Goswami

Consumer reviews online may contain suggestions useful for improving the target products and services. Mining suggestions is challenging because the ﬁeld lacks large labelled and balanced datasets. Furthermore, most prior studies have only focused on mining suggestions in a single domain. In this work, we introduce a novel up-sampling technique to address the problem of class imbalance, and propose a multi-task deep learning approach for mining suggestions from multiple domains. Experimental results on a publicly available dataset show that our up-sampling technique coupled with the multi-task framework outperforms state-of-the-art open domain suggestion mining models in terms of the F-1 measure and AUC.

PDF Details

AAAI Conference 2020 Conference Paper

Discriminating Cognitive Disequilibrium and Flow in Problem Solving: A Semi-Supervised Approach Using Involuntary Dynamic Behavioral Signals

Mononito Goswami
Lujie Chen
Artur Dubrawski

Problem solving is one of the most important 21st century skills. However, effectively coaching young students in problem solving is challenging because teachers must continuously monitor their cognitive and affective states, and make real-time pedagogical interventions to maximize their learning outcomes. It is an even more challenging task in social environments with limited human coaching resources. To lessen the cognitive load on a teacher and enable affect-sensitive intelligent tutoring, many researchers have investigated automated cognitive and affective detection methods. However, most of the studies use culturally-sensitive indices of affect that are prone to social editing such as facial expressions, and only few studies have explored involuntary dynamic behavioral signals such as gross body movements. In addition, most current methods rely on expensive labelled data from trained annotators for supervised learning. In this paper, we explore a semi-supervised learning framework that can learn low-dimensional representations of involuntary dynamic behavioral signals (mainly gross-body movements) from a modest number of short time series segments. Experiments on a real-world dataset reveal a signiﬁcant advantage of these representations in discriminating cognitive disequilibrium and ﬂow, as compared to traditional complexity measures from dynamical systems literature, and demonstrate their potential in transferring learned models to previously unseen subjects.

PDF Details

AAAI Conference 2020 Short Paper

Modeling Involuntary Dynamic Behaviors to Support Intelligent Tutoring (Student Abstract)

Mononito Goswami
Lujie Chen
Chufan Gao
Artur Dubrawski

Problem solving is one of the most important 21st century skills. However, effectively coaching young students in problem solving is challenging because teachers must continuously monitor their cognitive and affective states and make real-time pedagogical interventions to maximize students’ learning outcomes. It is an even more challenging task in social environments with limited human coaching resources. To lessen the cognitive load on a teacher and enable affectsensitive intelligent tutoring, many researchers have investigated automated cognitive and affective detection methods. However, most of the studies use culturally-sensitive indices of affect that are prone to social editing such as facial expressions, and only few studies have explored involuntary dynamic behavioral signals such as gross body movements. In addition, most current methods rely on expensive labelled data from trained annotators for supervised learning. In this paper, we explore a semi-supervised learning framework that can learn low-dimensional representations of involuntary dynamic behavioral signals (mainly gross-body movements) from a modest number of short time series segments. Experiments on a real-world dataset reveal a signiﬁcant utility of these representations in discriminating cognitive disequilibrium and ﬂow and demonstrate their potential in transferring learned models to previously unseen subjects.

PDF Details

ECAI Conference 2020 Conference Paper

What Makes a Better Companion? Towards Social & Engaging Peer Learning

Rajni Jindal
Maitree Leekha
Minkush Manuja
Mononito Goswami

Peer learning companions such as interactive tablets and social robots have shown great promise in supporting language development in young children. However, studies have shown that the perceived credibility of a robot as an educator and peer companion is contingent on how socially it behaves. We specifically focus on two roles of a peer learning companion- as an engaging storyteller and active listener. To this end, we develop models to predict whether the listener will lose attention (Listener Disengagement Prediction, LDP) and whether the robot should generate listener backchannels with high probability (Backchanneling Extent Prediction, BEP) during a specific time window. We formulate LDP and BEP as Time Series Classification problems and through extensive evaluation in multiple experimental settings, demonstrate our models’ promising results. Inspired by prior work, we also investigate socio-demographic and developmental features, which may give rise to variations in children’s backchanneling responses. Moreover, we examine critical features responsible for the predictive utility of our models using Permutation Feature Importance and Partial Dependency Plots. Our findings suggest that features such as pupil dilation, blink rate, acceleration of head, gaze direction, and some facial action units which have not been considered in prior work, are in fact, critical in predicting backchanneling extent and listener disengagement.

Details

AAAI Conference 2019 Short Paper

What’s Most Broken? A Tool to Assist Data-Driven Iterative Improvement of an Intelligent Tutoring System

Mononito Goswami
Shiven Mian
Jack Mostow

Intelligent Tutoring Systems (ITS) have great potential to change the educational landscape by bringing scientifically tested one-to-one tutoring to remote and under-served areas. However, effective ITSs are too complex to perfect. Instead, a practical guiding principle for ITS development and improvement is to fix what’s most broken. In this paper we present SPOT (Statistical Probe of Tutoring): a tool that mines data logged by an Intelligent Tutoring System to identify the ‘hot spots’ most detrimental to its efficiency and effectiveness in terms of its software reliability, usability, task difficulty, student engagement, and other criteria. SPOT uses heuristics and machine learning to discover, characterize, and prioritize such hot spots in order to focus ITS refinement on what matters most. We applied SPOT to data logged by RoboTutor, an ITS that teaches children basic reading, writing and arithmetic.

PDF Details