Transfer learning is a cornerstone of modern machine learning, promising a way to adapt models pretrained on a broad mix of data to new tasks with minimal new data. However, a significant challenge remains in ensuring that transferred features are sufficient to handle unseen datasets, amplified by the difficulty of quantifying whether two tasks are "related". To address these challenges, we evaluate model transfer from a pretraining mixture to each of its component tasks, assessing whether pretrained features can match the performance of task-specific direct training. We identify a fundamental limitation in deep learning models -- an "information saturation bottleneck" -- where networks fail to learn new features once they encode similar competing features during training. When restricted to learning only a subset of key features during pretraining, models will permanently lose critical features for transfer and perform inconsistently on data distributions, even components of the training mixture. Empirical evidence from published studies suggests that this phenomenon is pervasive in deep learning architectures -- factors such as data distribution or ordering affect the features that current representation learning methods can learn over time. This study suggests that relying solely on large-scale networks may not be as effective as focusing on task-specific training, when available. We propose richer feature representations as a potential solution to better generalize across new datasets and, specifically, present existing methods alongside a novel approach, the initial steps towards addressing this challenge.
Efficient simulation of Laser Powder Bed Fusion (LPBF) is crucial for process prediction due to the lasting issue of high computation cost using traditional numerical methods such as finite element analysis (FEA). This study presents an efficient modeling framework termed FEA-Regulated Physics-Informed Neural Network (FEA-PINN) to accelerate the thermal field prediction in a LPBF process while maintaining the FEA accuracy. A novel dynamic material updating strategy is developed to capture the dynamic phase change of powder-liquid-solid in the PINN model. The PINN model incorporates temperature-dependent material properties and phase change behavior using the apparent heat capacity method. While the PINN model demonstrates high accuracy with a small training data and enables generalization of new process parameters via transfer learning, it faces the challenge of high computation cost in time-dependent problems due to the residual accumulation. To overcome this issue, the FEA-PINN framework integrates corrective FEA simulations during inference to enforce physical consistency and reduce error drift. A comparative analysis shows that FEA-PINN achieves equivalent accuracy to FEA while significantly reducing computational cost. The framework has been validated using the benchmark FEA data and demonstrated through single-track scanning in LPBF.
Automated fundus image quality assessment (FIQA) remains a challenge due to variations in image acquisition and subjective expert evaluations. We introduce FundaQ-8, a novel expert-validated framework for systematically assessing fundus image quality using eight critical parameters, including field coverage, anatomical visibility, illumination, and image artifacts. Using FundaQ-8 as a structured scoring reference, we develop a ResNet18-based regression model to predict continuous quality scores in the 0 to 1 range. The model is trained on 1800 fundus images from real-world clinical sources and Kaggle datasets, using transfer learning, mean squared error optimization, and standardized preprocessing. Validation against the EyeQ dataset and statistical analyses confirm the framework's reliability and clinical interpretability. Incorporating FundaQ-8 into deep learning models for diabetic retinopathy grading also improves diagnostic robustness, highlighting the value of quality-aware training in real-world screening applications.
The growing adoption of Artificial Intelligence (AI) in Internet of Things (IoT) ecosystems has intensified the need for personalized learning methods that can operate efficiently and privately across heterogeneous, resource-constrained devices. However, enabling effective personalized learning in decentralized settings introduces several challenges, including efficient knowledge transfer between clients, protection of data privacy, and resilience against poisoning attacks. In this paper, we address these challenges by developing P4 (Personalized, Private, Peer-to-Peer) -- a method designed to deliver personalized models for resource-constrained IoT devices while ensuring differential privacy and robustness against poisoning attacks. Our solution employs a lightweight, fully decentralized algorithm to privately detect client similarity and form collaborative groups. Within each group, clients leverage differentially private knowledge distillation to co-train their models, maintaining high accuracy while ensuring robustness to the presence of malicious clients. We evaluate P4 on popular benchmark datasets using both linear and CNN-based architectures across various heterogeneity settings and attack scenarios. Experimental results show that P4 achieves 5% to 30% higher accuracy than leading differentially private peer-to-peer approaches and maintains robustness with up to 30% malicious clients. Additionally, we demonstrate its practicality by deploying it on resource-constrained devices, where collaborative training between two clients adds only ~7 seconds of overhead.
This research presents the development of an Artificial Intelligence (AI) - driven crop disease detection system designed to assist farmers in rural areas with limited resources. We aim to compare different deep learning models for a comparative analysis, focusing on their efficacy in transfer learning. By leveraging deep learning models, including EfficientNet, ResNet101, MobileNetV2, and our custom CNN, which achieved a validation accuracy of 95.76%, the system effectively classifies plant diseases. This research demonstrates the potential of transfer learning in reshaping agricultural practices, improving crop health management, and supporting sustainable farming in rural environments.
While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning, memory, and tool use, remains relatively underexplored. Existing agent distillation methods typically replay full teacher trajectories or imitate step-by-step teacher tool usage, but they often struggle to train student agents to dynamically plan and act in novel environments. We propose AgentDistill, a novel, training-free agent distillation framework that enables efficient and scalable knowledge transfer via direct reuse of Model-Context-Protocols (MCPs), which are structured and reusable task-solving modules autonomously generated by teacher agents. The reuse of these distilled MCPs enables student agents to generalize their capabilities across domains and solve new problems with minimal supervision or human intervention. Experiments on biomedical and mathematical benchmarks demonstrate that our distilled student agents, built on small language models, can achieve performance comparable to advanced systems using large LLMs such as OctoTools (GPT-4o), highlighting the effectiveness of our framework in building scalable and cost-efficient intelligent agents.
There is growing interest in extending average treatment effect (ATE) estimation to incorporate non-tabular data, such as images and text, which may act as sources of confounding. Neglecting these effects risks biased results and flawed scientific conclusions. However, incorporating non-tabular data necessitates sophisticated feature extractors, often in combination with ideas of transfer learning. In this work, we investigate how latent features from pre-trained neural networks can be leveraged to adjust for sources of confounding. We formalize conditions under which these latent features enable valid adjustment and statistical inference in ATE estimation, demonstrating results along the example of double machine learning. We discuss critical challenges inherent to latent feature learning and downstream parameter estimation arising from the high dimensionality and non-identifiability of representations. Common structural assumptions for obtaining fast convergence rates with additive or sparse linear models are shown to be unrealistic for latent features. We argue, however, that neural networks are largely insensitive to these issues. In particular, we show that neural networks can achieve fast convergence rates by adapting to intrinsic notions of sparsity and dimension of the learning problem.
Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of expert models and adapters, often shared via platforms like HuggingFace and AdapterHub. To leverage these resources, numerous model upcycling methods have emerged, enabling the reuse of fine-tuned models in multi-task systems. A natural pipeline has thus formed to harness the benefits of transfer learning and amortize sunk training costs: models are pre-trained on general data, fine-tuned on specific tasks, and then upcycled into more general-purpose systems. A prevailing assumption is that improvements at one stage of this pipeline propagate downstream, leading to gains at subsequent steps. In this work, we challenge that assumption by examining how expert fine-tuning affects model upcycling. We show that long fine-tuning of experts that optimizes for their individual performance leads to degraded merging performance, both for fully fine-tuned and LoRA-adapted models, and to worse downstream results when LoRA adapters are upcycled into MoE layers. We trace this degradation to the memorization of a small set of difficult examples that dominate late fine-tuning steps and are subsequently forgotten during merging. Finally, we demonstrate that a task-dependent aggressive early stopping strategy can significantly improve upcycling performance.
This thesis addresses the technical challenges of applying machine learning to understand and interpret medical audio signals. The sounds of our lungs, heart, and voice convey vital information about our health. Yet, in contemporary medicine, these sounds are primarily analyzed through auditory interpretation by experts using devices like stethoscopes. Automated analysis offers the potential to standardize the processing of medical sounds, enable screening in low-resource settings where physicians are scarce, and detect subtle patterns that may elude human perception, thereby facilitating early diagnosis and treatment. Focusing on the analysis of infant cry sounds to predict medical conditions, this thesis contributes on four key fronts. First, in low-data settings, we demonstrate that large databases of adult speech can be harnessed through neural transfer learning to develop more accurate and robust models for infant cry analysis. Second, in cost-effective modeling, we introduce an end-to-end model compression approach for recurrent networks using tensor decomposition. Our method requires no post-hoc processing, achieves compression rates of several hundred-fold, and delivers accurate, portable models suitable for resource-constrained devices. Third, we propose novel domain adaptation techniques tailored for audio models and adapt existing methods from computer vision. These approaches address dataset bias and enhance generalization across domains while maintaining strong performance on the original data. Finally, to advance research in this domain, we release a unique, open-source dataset of infant cry sounds, developed in collaboration with clinicians worldwide. This work lays the foundation for recognizing the infant cry as a vital sign and highlights the transformative potential of AI-driven audio monitoring in shaping the future of accessible and affordable healthcare.
Transferring extensive knowledge from relevant social networks has emerged as a promising solution to overcome label scarcity in detecting social bots and other anomalies with GNN-based models. However, effective transfer faces two critical challenges. Firstly, the network heterophily problem, which is caused by bots hiding malicious behaviors via indiscriminately interacting with human users, hinders the model's ability to learn sufficient and accurate bot-related knowledge from source domains. Secondly, single-source transfer might lead to inferior and unstable results, as the source network may embody weak relevance to the task and provide limited knowledge. To address these challenges, we explore multiple source domains and propose a multi-source graph domain adaptation model named \textit{BotTrans}. We initially leverage the labeling knowledge shared across multiple source networks to establish a cross-source-domain topology with increased network homophily. We then aggregate cross-domain neighbor information to enhance the discriminability of source node embeddings. Subsequently, we integrate the relevance between each source-target pair with model optimization, which facilitates knowledge transfer from source networks that are more relevant to the detection task. Additionally, we propose a refinement strategy to improve detection performance by utilizing semantic knowledge within the target domain. Extensive experiments on real-world datasets demonstrate that \textit{BotTrans} outperforms the existing state-of-the-art methods, revealing its efficacy in leveraging multi-source knowledge when the target detection task is unlabeled.
Large Language Models (LLMs) have demonstrated significant strides across various information retrieval tasks, particularly as rerankers, owing to their strong generalization and knowledge-transfer capabilities acquired from extensive pretraining. In parallel, the rise of LLM-based chat interfaces has raised user expectations, encouraging users to pose more complex queries that necessitate retrieval by ``reasoning'' over documents rather than through simple keyword matching or semantic similarity. While some recent efforts have exploited reasoning abilities of LLMs for reranking such queries, considerable potential for improvement remains. In that regards, we introduce InsertRank, an LLM-based reranker that leverages lexical signals like BM25 scores during reranking to further improve retrieval performance. InsertRank demonstrates improved retrieval effectiveness on -- BRIGHT, a reasoning benchmark spanning 12 diverse domains, and R2MED, a specialized medical reasoning retrieval benchmark spanning 8 different tasks. We conduct an exhaustive evaluation and several ablation studies and demonstrate that InsertRank consistently improves retrieval effectiveness across multiple families of LLMs, including GPT, Gemini, and Deepseek models. %In addition, we also conduct ablation studies on normalization by varying the scale of the BM25 scores, and positional bias by shuffling the order of the documents. With Deepseek-R1, InsertRank achieves a score of 37.5 on the BRIGHT benchmark. and 51.1 on the R2MED benchmark, surpassing previous methods.
Depth estimation is crucial for intelligent systems, enabling applications from autonomous navigation to augmented reality. While traditional stereo and active depth sensors have limitations in cost, power, and robustness, dual-pixel (DP) technology, ubiquitous in modern cameras, offers a compelling alternative. This paper introduces DiFuse-Net, a novel modality decoupled network design for disentangled RGB and DP based depth estimation. DiFuse-Net features a window bi-directional parallax attention mechanism (WBiPAM) specifically designed to capture the subtle DP disparity cues unique to smartphone cameras with small aperture. A separate encoder extracts contextual information from the RGB image, and these features are fused to enhance depth prediction. We also propose a Cross-modal Transfer Learning (CmTL) mechanism to utilize large-scale RGB-D datasets in the literature to cope with the limitations of obtaining large-scale RGB-DP-D dataset. Our evaluation and comparison of the proposed method demonstrates its superiority over the DP and stereo-based baseline methods. Additionally, we contribute a new, high-quality, real-world RGB-DP-D training dataset, named Dual-Camera Dual-Pixel (DCDP) dataset, created using our novel symmetric stereo camera hardware setup, stereo calibration and rectification protocol, and AI stereo disparity estimation method.
This paper introduces GUST (Generative Uncertainty learning via Self-supervised pretraining and Transfer learning), a framework for quantifying free-form geometric uncertainties inherent in the manufacturing of metamaterials. GUST leverages the representational power of deep generative models to learn a high-dimensional conditional distribution of as-fabricated unit cell geometries given nominal designs, thereby enabling uncertainty quantification. To address the scarcity of real-world manufacturing data, GUST employs a two-stage learning process. First, it leverages self-supervised pretraining on a large-scale synthetic dataset to capture the structure variability inherent in metamaterial geometries and an approximated distribution of as-fabricated geometries given nominal designs. Subsequently, GUST employs transfer learning by fine-tuning the pretrained model on limited real-world manufacturing data, allowing it to adapt to specific manufacturing processes and nominal designs. With only 960 unit cells additively manufactured in only two passes, GUST can capture the variability in geometry and effective material properties. In contrast, directly training a generative model on the same amount of real-world data proves insufficient, as demonstrated through both qualitative and quantitative comparisons. This scalable and cost-effective approach significantly reduces data requirements while maintaining the effectiveness in learning complex, real-world geometric uncertainties, offering an affordable method for free-form geometric uncertainty quantification in the manufacturing of metamaterials. The capabilities of GUST hold significant promise for high-precision industries such as aerospace and biomedical engineering, where understanding and mitigating manufacturing uncertainties are critical.
Spiking Neural Networks (SNNs), known for their potential to enable low energy consumption and computational cost, can bring significant advantages to the realm of embedded machine learning for edge applications. However, input coming from standard digital sensors must be encoded into spike trains before it can be elaborated with neuromorphic computing technologies. We present here a detailed comparison of available spike encoding techniques for the translation of time-varying signals into the event-based signal domain, tested on two different datasets both acquired through commercially available digital devices: the Free Spoken Digit dataset (FSD), consisting of 8-kHz audio files, and the WISDM dataset, composed of 20-Hz recordings of human activity through mobile and wearable inertial sensors. We propose a complete pipeline to benchmark these encoding techniques by performing time-dependent signal classification through a Spiking Convolutional Neural Network (sCNN), including a signal preprocessing step consisting of a bank of filters inspired by the human cochlea, feature extraction by production of a sonogram, transfer learning via an equivalent ANN, and model compression schemes aimed at resource optimization. The resulting performance comparison and analysis provides a powerful practical tool, empowering developers to select the most suitable coding method based on the type of data and the desired processing algorithms, and further expands the applicability of neuromorphic computational paradigms to embedded sensor systems widely employed in the IoT and industrial domains.
Machine learning has promised to change the landscape of laboratory chemistry, with impressive results in molecular property prediction and reaction retro-synthesis. However, chemical datasets are often inaccessible to the machine learning community as they tend to require cleaning, thorough understanding of the chemistry, or are simply not available. In this paper, we introduce a novel dataset for yield prediction, providing the first-ever transient flow dataset for machine learning benchmarking, covering over 1200 process conditions. While previous datasets focus on discrete parameters, our experimental set-up allow us to sample a large number of continuous process conditions, generating new challenges for machine learning models. We focus on solvent selection, a task that is particularly difficult to model theoretically and therefore ripe for machine learning applications. We showcase benchmarking for regression algorithms, transfer-learning approaches, feature engineering, and active learning, with important applications towards solvent replacement and sustainable manufacturing.
Transfer learning, a technique commonly used in generative artificial intelligence, allows neural network models to bring prior knowledge to bear when learning a new task. This study demonstrates that transfer learning significantly enhances the accuracy of sleep-stage decoding from peripheral wearable devices by leveraging neural network models pretrained on electroencephalographic (EEG) signals. Consumer wearable technologies typically rely on peripheral physiological signals such as pulse plethysmography (PPG) and respiratory data, which, while convenient, lack the fidelity of clinical electroencephalography (EEG) for detailed sleep-stage classification. We pretrained a transformer-based neural network on a large, publicly available EEG dataset and subsequently fine-tuned this model on noisier peripheral signals. Our transfer learning approach improved overall classification accuracy from 67.6\% (baseline model trained solely on peripheral signals) to 76.6\%. Notable accuracy improvements were observed across sleep stages, particularly lighter sleep stages such as REM and N1. These results highlight transfer learning's potential to substantially enhance the accuracy and utility of consumer wearable devices without altering existing hardware. Future integration of self-supervised learning methods may further boost performance, facilitating more precise, longitudinal sleep monitoring for personalized health applications.
Prioritizing methane for near-term climate action is crucial due to its significant impact on global warming. Previous work used columnwise matched filter products from the airborne AVIRIS-NG imaging spectrometer to detect methane plume sources; convolutional neural networks (CNNs) discerned anthropogenic methane plumes from false positive enhancements. However, as an increasing number of remote sensing platforms are used for methane plume detection, there is a growing need to address cross-platform alignment. In this work, we describe model- and data-driven machine learning approaches that leverage airborne observations to improve spaceborne methane plume detection, reconciling the distributional shifts inherent with performing the same task across platforms. We develop a spaceborne methane plume classifier using data from the EMIT imaging spectroscopy mission. We refine classifiers trained on airborne imagery from AVIRIS-NG campaigns using transfer learning, outperforming the standalone spaceborne model. Finally, we use CycleGAN, an unsupervised image-to-image translation technique, to align the data distributions between airborne and spaceborne contexts. Translating spaceborne EMIT data to the airborne AVIRIS-NG domain using CycleGAN and applying airborne classifiers directly yields the best plume detection results. This methodology is useful not only for data simulation, but also for direct data alignment. Though demonstrated on the task of methane plume detection, our work more broadly demonstrates a data-driven approach to align related products obtained from distinct remote sensing instruments.
The System to Augment Restorative Sleep (StARS) is a modular hardware/software platform designed for real-time sleep monitoring and intervention. Utilizing the compact DCM biosignal device, StARS captures electrophysiological signals (EEG, EMG, EOG) and synchronizes sensor data using the ezmsg real-time software framework. StARS supports interventions such as closed-loop auditory stimulation and dynamic thermal modulation guided by sleep-stage decoding via advanced neural network models and transfer learning. Configurable with a lightweight EEG forehead patch or wearable sensors like smart rings, StARS offers flexible, low-burden solutions for EEG, BCI, and sleep-enhancement research and applications. The open-source DCM patch further enables customizable EEG device development.
Retinal diseases such as Diabetic Retinopathy (DR) and Macular Hole (MH) significantly impact vision and affect millions worldwide. Early detection is crucial, as DR, a complication of diabetes, damages retinal blood vessels, potentially leading to blindness, while MH disrupts central vision, affecting tasks like reading and facial recognition. This paper employed two lightweight and efficient Convolution Neural Network architectures, MobileNet and NASNetMobile, for the classification of Normal, DR, and MH retinal images. The models were trained on the RFMiD dataset, consisting of 3,200 fundus images, after undergoing preprocessing steps such as resizing, normalization, and augmentation. To address data scarcity, this study leveraged transfer learning and data augmentation techniques, enhancing model generalization and performance. The experimental results demonstrate that MobileNetV2 achieved the highest accuracy of 90.8%, outperforming NASNetMobile, which achieved 89.5% accuracy. These findings highlight the effectiveness of CNNs in retinal disease classification, providing a foundation for AI-assisted ophthalmic diagnosis and early intervention.
Early and accurate detection of brain abnormalities, such as tumors and strokes, is essential for timely intervention and improved patient outcomes. In this study, we present a deep learning-based system capable of identifying both brain tumors and strokes from MRI images, along with their respective stages. We have executed two groundbreaking strategies involving convolutional neural networks, MobileNet V2 and ResNet-50-optimized through transfer learning to classify MRI scans into five diagnostic categories. Our dataset, aggregated and augmented from various publicly available MRI sources, was carefully curated to ensure class balance and image diversity. To enhance model generalization and prevent overfitting, we applied dropout layers and extensive data augmentation. The models achieved strong performance, with training accuracy reaching 93\% and validation accuracy up to 88\%. While ResNet-50 demonstrated slightly better results, Mobile Net V2 remains a promising option for real-time diagnosis in low resource settings due to its lightweight architecture. This research offers a practical AI-driven solution for early brain abnormality detection, with potential for clinical deployment and future enhancement through larger datasets and multi modal inputs.