Publications
Tagged As
Improving long-text authorship verification via model selection and data tuning
May 5, 2023
Conference Paper
Published in:
Proc. 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, LaTeCH-CLfL2023, 5 May 2023, pp. 28-37.
Topic:
R&D area:
Summary
Authorship verification is used to link texts written by the same author without needing a model per author, making it useful for deanonymizing users spreading text with malicious intent. Recent advances in Transformer-based language models hold great promise for author verification, though short context lengths and non-diverse training regimes present challenges for their practical application. In this work, we investigate the effect of these challenges in the application of a Cross-Encoder Transformer-based author verification system under multiple conditions. We perform experiments with four Transformer backbones using differently tuned variants of fanfiction data and found that our BigBird pipeline outperformed Longformer, RoBERTa, and ELECTRA and performed competitively against the official top ranked system from the PAN evaluation. We also examined the effect of authors and fandoms not seen in training on model performance. Through this, we found fandom has the greatest influence on true trials, pairs of text written by the same author, and that a balanced training dataset in terms of class and fandom performed the most consistently.
Summary
Authorship verification is used to link texts written by the same author without needing a model per author, making it useful for deanonymizing users spreading text with malicious intent. Recent advances in Transformer-based language models hold great promise for author verification, though short context lengths and non-diverse training regimes present...
READ MORE
System analysis for responsible design of modern AI/ML systems
April 19, 2022
Journal Article
Published in:
arXiv, April 19, 2022.
Summary
The irresponsible use of ML algorithms in practical settings has received a lot of deserved attention in the recent years. We posit that the traditional system analysis perspective is needed when designing and implementing ML algorithms and systems. Such perspective can provide a formal way for evaluating and enabling responsible ML practices. In this paper, we review components of the System Analysis methodology and highlight how they connect and enable responsible practices of ML design.
Summary
The irresponsible use of ML algorithms in practical settings has received a lot of deserved attention in the recent years. We posit that the traditional system analysis perspective is needed when designing and implementing ML algorithms and systems. Such perspective can provide a formal way for evaluating and enabling responsible...
READ MORE
Quantifying bias in face verification system
April 1, 2022
Journal Article
Published in:
Comput. Sci. Math. Forum 2022, 3(1), 6
Topic:
R&D area:
Summary
Machine learning models perform face verification (FV) for a variety of highly consequential applications, such as biometric authentication, face identification, and surveillance. Many state-of-the-art FV systems suffer from unequal performance across demographic groups, which is commonly overlooked by evaluation measures that do not assess population-specific performance. Deployed systems with bias may result in serious harm against individuals or groups who experience underperformance. We explore several fairness definitions and metrics, attempting to quantify bias in Google’s FaceNet model. In addition to statistical fairness metrics, we analyze clustered face embeddings produced by the FV model. We link well-clustered embeddings (well-defined, dense clusters) for a demographic group to biased model performance against that group. We present the intuition that FV systems underperform on protected demographic groups because they are less sensitive to differences between features within those groups, as evidenced by clustered embeddings. We show how this performance discrepancy results from a combination of representation and aggregation bias.
Summary
Machine learning models perform face verification (FV) for a variety of highly consequential applications, such as biometric authentication, face identification, and surveillance. Many state-of-the-art FV systems suffer from unequal performance across demographic groups, which is commonly overlooked by evaluation measures that do not assess population-specific performance. Deployed systems with bias...
READ MORE
Adapting deep learning models to new meteorological contexts using transfer learning
December 15, 2021
Conference Paper
Published in:
2021 IEEE International Conference on Big Data (Big Data), 2021, pp. 4169-4177, doi: 10.1109/BigData52589.2021.9671451.
Summary
Meteorological applications such as precipitation nowcasting, synthetic radar generation, statistical downscaling and others have benefited from deep learning (DL) approaches, however several challenges remain for widespread adaptation of these complex models in operational systems. One of these challenges is adequate generalizability; deep learning models trained from datasets collected in specific contexts should not be expected to perform as well when applied to different contexts required by large operational systems. One obvious mitigation for this is to collect massive amounts of training data that cover all expected meteorological contexts, however this is not only costly and difficult to manage, but is also not possible in many parts of the globe where certain sensing platforms are sparse. In this paper, we describe an application of transfer learning to perform domain transfer for deep learning models. We demonstrate a transfer learning algorithm called weight superposition to adapt a Convolutional Neural Network trained in a source context to a new target context. Weight superposition is a method for storing multiple models within a single set of parameters thus greatly simplifying model maintenance and training. This approach also addresses the issue of catastrophic forgetting where a model, once adapted to a new context, performs poorly in the original context. We apply weight superposition to the problem of synthetic weather radar generation and show that in scenarios where the target context has less data, a model adapted with weight superposition is better at maintaining performance when compared to simpler methods. Conversely, the simple adapted model performs better on the source context when the source and target contexts have comparable amounts of data.
Summary
Meteorological applications such as precipitation nowcasting, synthetic radar generation, statistical downscaling and others have benefited from deep learning (DL) approaches, however several challenges remain for widespread adaptation of these complex models in operational systems. One of these challenges is adequate generalizability; deep learning models trained from datasets collected in specific...
READ MORE
Selective network discovery via deep reinforcement learning on embedded spaces
December 1, 2021
Conference Paper
Published in:
Appl. Netw. Sci., Vol. 6, No.1, December 2021, Art. No. 24.
Summary
Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algorithms optimized for specific downstream learning tasks given resource collection constraints are of great interest. In this paper, we formulate the task-specific network discovery problem as a sequential decision-making problem. Our downstream task is selective harvesting, the optimal collection of vertices with a particular attribute. We propose a framework, called network actor critic (NAC), which learns a policy and notion of future reward in an offline setting via a deep reinforcement learning algorithm. The NAC paradigm utilizes a task-specific network embedding to reduce the state space complexity. A detailed comparative analysis of popular network embeddings is presented with respect to their role in supporting offline planning. Furthermore, a quantitative study is presented on various synthetic and real benchmarks using NAC and several baselines. We show that offline models of reward and network discovery policies lead to significantly improved performance when compared to competitive online discovery algorithms. Finally, we outline learning regimes where planning is critical in addressing sparse and changing reward signals.
Summary
Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algorithms optimized for specific downstream...
READ MORE
Application of complex split-activation feedforward networks to beamforming
October 31, 2021
Conference Paper
Published in:
55th Asilomar Conf. on Signals, Systems and Computers, ACSSC, 31 October - 3 November 2021.
Topic:
R&D area:
R&D group:
Summary
In increasingly congested RF environments and for jamming at closer ranges, amplifiers may introduce nonlinearities that linear adaptive beamforming techniques can't mitigate. Machine learning architectures are intended to solve such nonlinear least squares problems, but much of the current work and available software is limited to signals represented as real sequences. In this paper, neural networks using complex numbers to represent the complex baseband RF signals are considered. A complex backpropagation approach that calculates gradients and a Jacobian, allows for fast optimization of the neural networks. Through simulations, it is shown that complex neural networks require less training samples than their real counterparts and may generalize better in dynamic environments.
Summary
In increasingly congested RF environments and for jamming at closer ranges, amplifiers may introduce nonlinearities that linear adaptive beamforming techniques can't mitigate. Machine learning architectures are intended to solve such nonlinear least squares problems, but much of the current work and available software is limited to signals represented as real...
READ MORE
Detecting pathogen exposure during the non-symptomatic incubation period using physiological data: proof of concept in non-human primates
September 3, 2021
Journal Article
Published in:
Front Physiol., Vol. 12, September 2021, Article 691074.
Summary
Background and Objectives: Early warning of bacterial and viral infection, prior to the development of overt clinical symptoms, allows not only for improved patient care and outcomes but also enables faster implementation of public health measures (patient isolation and contact tracing). Our primary objectives in this effort are 3-fold. First, we seek to determine the upper limits of early warning detection through physiological measurements. Second, we investigate whether the detected physiological response is specific to the pathogen. Third, we explore the feasibility of extending early warning detection with wearable devices. Research Methods: For the first objective, we developed a supervised random forest algorithm to detect pathogen exposure in the asymptomatic period prior to overt symptoms (fever). We used high-resolution physiological telemetry data (aortic blood pressure, intrathoracic pressure, electrocardiograms, and core temperature) from non-human primate animal models exposed to two viral pathogens: Ebola and Marburg (N = 20). Second, to determine reusability across different pathogens, we evaluated our algorithm against three independent physiological datasets from non-human primate models (N = 13) exposed to three different pathogens: Lassa and Nipah viruses and Y. pestis. For the third objective, we evaluated performance degradation when the algorithm was restricted to features derived from electrocardiogram (ECG) waveforms to emulate data from a non-invasive wearable device. Results: First, our cross-validated random forest classifier provides a mean early warning of 51 ± 12 h, with an area under the receiver-operating characteristic curve (AUC) of 0.93 ± 0.01. Second, our algorithm achieved comparable performance when applied to datasets from different pathogen exposures – a mean early warning of 51 ± 14 h and AUC of 0.95 ± 0.01. Last, with a degraded feature set derived solely from ECG, we observed minimal degradation – a mean early warning of 46 ± 14 h and AUC of 0.91 ± 0.001. Conclusion: Under controlled experimental conditions, physiological measurements can provide over 2 days of early warning with high AUC. Deviations in physiological signals following exposure to a pathogen are due to the underlying host’s immunological response and are not specific to the pathogen. Pre-symptomatic detection is strong even when features are limited to ECG-derivatives, suggesting that this approach may translate to non-invasive wearable devices.
Summary
Background and Objectives: Early warning of bacterial and viral infection, prior to the development of overt clinical symptoms, allows not only for improved patient care and outcomes but also enables faster implementation of public health measures (patient isolation and contact tracing). Our primary objectives in this effort are 3-fold. First...
READ MORE
Development of a field artifical intelligence triage tool: Confidence in the prediction of shock, transfusion, and definitive surgical therapy in patients with truncal gunshot wounds
June 1, 2021
Journal Article
Published in:
J. Trauma Acute Care Surg., Vol. 90, No. 6, 1 June 2021.
Topic:
R&D area:
Summary
BACKGROUND: In-field triage tools for trauma patients are limited by availability of information, linear risk classification, and a lack of confidence reporting. We therefore set out to develop and test a machine learning algorithm that can overcome these limitations by accurately and confidently making predictions to support in-field triage in the first hours after traumatic injury. METHODS: Using an American College of Surgeons Trauma Quality Improvement Program-derived database of truncal and junctional gunshot wound (GSW) patients (aged 1~0 years), we trained an information-aware Dirichlet deep neural network (field artificial intelligence triage). Using supervised training, field artificial intelligence triage was trained to predict shock and the need for major hemorrhage control procedures or early massive transfusion (MT) using GSW anatomical locations, vital signs, and patient information available in the field. In parallel, a confidence model was developed to predict the true-dass probability ( scale of 0-1 ), indicating the likelihood that the prediction made was correct, based on the values and interconnectivity of input variables.
Summary
BACKGROUND: In-field triage tools for trauma patients are limited by availability of information, linear risk classification, and a lack of confidence reporting. We therefore set out to develop and test a machine learning algorithm that can overcome these limitations by accurately and confidently making predictions to support in-field triage in...
READ MORE
Health-informed policy gradients for multi-agent reinforcement learning
April 1, 2021
Journal Article
Published in:
https://arxiv.org/abs/1908.01022
Summary
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on simple particle environments that have elements of system health, risk-taking, semi-expendable agents, and partial observability. We show significant improvement in learning performance compared to policy gradient methods that do not perform multi-agent credit assignment.
Summary
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then...
READ MORE
Principles for evaluation of AI/ML model performance and robustness, revision 1
March 30, 2021
Project Report
Published in:
MIT Lincoln Laboratory Report MD-62
Summary
The Department of Defense (DoD) has significantly increased its investment in the design, evaluation, and deployment of Artificial Intelligence and Machine Learning (AI/ML) capabilities to address national security needs. While there are numerous AI/ML successes in the academic and commercial sectors, many of these systems have also been shown to be brittle and nonrobust. In a complex and ever-changing national security environment, it is vital that the DoD establish a sound and methodical process to evaluate the performance and robustness of AI/ML models before these new capabilities are deployed to the field. Without an effective evaluation process, the DoD may deploy AI/ML models that are assumed to be effective given limited evaluation metrics but actually have poor performance and robustness on operational data. Poor evaluation practices lead to loss of trust in AI/ML systems by model operators and more frequent--often costly--design updates needed to address the evolving security environment. In contrast, an effective evaluation process can drive the design of more resilient capabilities, ag potential limitations of models before they are deployed, and build operator trust in AI/ML systems. This paper reviews the AI/ML development process, highlights common best practices for AI/ML model evaluation, and makes the following recommendations to DoD evaluators to ensure the deployment of robust AI/ML capabilities for national security needs: -Develop testing datasets with sufficient variation and number of samples to effectively measure the expected performance of the AI/ML model on future (unseen) data once deployed, -Maintain separation between data used for design and evaluation (i.e., the test data is not used to design the AI/ML model or train its parameters) in order to ensure an honest and unbiased assessment of the model's capability, -Evaluate performance given small perturbations and corruptions to data inputs to assess the smoothness of the AI/ML model and identify potential vulnerabilities, and -Evaluate performance on samples from data distributions that are shifted from the assumed distribution that was used to design the AI/ML model to assess how the model may perform on operational data that may differ from the training data. By following the recommendations for evaluation presented in this paper, the DoD can fully take advantage of the AI/ML revolution, delivering robust capabilities that maintain operational feasibility over longer periods of time, and increase warfighter confidence in AI/ML systems.
Summary
The Department of Defense (DoD) has significantly increased its investment in the design, evaluation, and deployment of Artificial Intelligence and Machine Learning (AI/ML) capabilities to address national security needs. While there are numerous AI/ML successes in the academic and commercial sectors, many of these systems have also been shown to...
READ MORE