We present RelBench, a public benchmark for solving predictive tasks over relational databases with graph neural networks. RelBench provides databases and tasks spanning diverse domains and scales, and is intended to be a foundational infrastructure for future research. We use RelBench to conduct the first comprehensive study of Relational Deep Learning (RDL) (Fey et al., 2024), which combines graph neural network predictive models with (deep) tabular models that extract initial entity-level representations from raw tables. End-to-end learned RDL models fully exploit the predictive signal encoded in primary-foreign key links, marking a significant shift away from the dominant paradigm of manual feature engineering combined with tabular models. To thoroughly evaluate RDL against this prior gold-standard, we conduct an in-depth user study where an experienced data scientist manually engineers features for each task. In this study, RDL learns better models whilst reducing human work needed by more than an order of magnitude. This demonstrates the power of deep learning for solving predictive tasks over relational databases, opening up many new research opportunities enabled by RelBench.
Medical image analysis using deep learning frameworks has advanced healthcare by automating complex tasks, but many existing frameworks lack flexibility, modularity, and user-friendliness. To address these challenges, we introduce Yucca, an open-source AI framework available at https://github.com/Sllambias/yucca, designed specifically for medical imaging applications and built on PyTorch and PyTorch Lightning. Yucca features a three-tiered architecture: Functional, Modules, and Pipeline, providing a comprehensive and customizable solution. Evaluated across diverse tasks such as cerebral microbleeds detection, white matter hyperintensity segmentation, and hippocampus segmentation, Yucca achieves state-of-the-art results, demonstrating its robustness and versatility. Yucca offers a powerful, flexible, and user-friendly platform for medical image analysis, inviting community contributions to advance its capabilities and impact.
Domain generalizability is a crucial aspect of a deep learning model since it determines the capability of the model to perform well on data from unseen domains. However, research on the domain generalizability of deep learning models for vision-language tasks remains limited, primarily because of the lack of required datasets. To address these challenges, we propose VolDoGer: Vision-Language Dataset for Domain Generalization, a dedicated dataset designed for domain generalization that addresses three vision-language tasks: image captioning, visual question answering, and visual entailment. We constructed VolDoGer by extending LLM-based data annotation techniques to vision-language tasks, thereby alleviating the burden of recruiting human annotators. We evaluated the domain generalizability of various models, ranging from fine-tuned models to a recent multimodal large language model, through VolDoGer.
Real-time lightweight time series anomaly detection has become increasingly crucial in cybersecurity and many other domains. Its ability to adapt to unforeseen pattern changes and swiftly identify anomalies enables prompt responses and critical decision-making. While several such anomaly detection approaches have been introduced in recent years, they primarily utilize a single type of recurrent neural networks (RNNs) and have been implemented in only one deep learning framework. It is unclear how the use of different types of RNNs available in various deep learning frameworks affects the performance of these anomaly detection approaches due to the absence of comprehensive evaluations. Arbitrarily choosing a RNN variant and a deep learning framework to implement an anomaly detection approach may not reflect its true performance and could potentially mislead users into favoring one approach over another. In this paper, we aim to study the influence of various types of RNNs available in popular deep learning frameworks on real-time lightweight time series anomaly detection. We reviewed several state-of-the-art approaches and implemented a representative anomaly detection approach using well-known RNN variants supported by three widely recognized deep learning frameworks. A comprehensive evaluation is then conducted to analyze the performance of each implementation across real-world, open-source time series datasets. The evaluation results provide valuable guidance for selecting the appropriate RNN variant and deep learning framework for real-time, lightweight time series anomaly detection.
This book provides an introduction to the mathematical analysis of deep learning. It covers fundamental results in approximation theory, optimization theory, and statistical learning theory, which are the three main pillars of deep neural network theory. Serving as a guide for students and researchers in mathematics and related fields, the book aims to equip readers with foundational knowledge on the topic. It prioritizes simplicity over generality, and presents rigorous yet accessible results to help build an understanding of the essential mathematical concepts underpinning deep learning.
Tipping points occur in many real-world systems, at which the system shifts suddenly from one state to another. The ability to predict the occurrence of tipping points from time series data remains an outstanding challenge and a major interest in a broad range of research fields. Particularly, the widely used methods based on bifurcation theory are neither reliable in prediction accuracy nor applicable for irregularly-sampled time series which are commonly observed from real-world systems. Here we address this challenge by developing a deep learning algorithm for predicting the occurrence of tipping points in untrained systems, by exploiting information about normal forms. Our algorithm not only outperforms traditional methods for regularly-sampled model time series but also achieves accurate predictions for irregularly-sampled model time series and empirical time series. Our ability to predict tipping points for complex systems paves the way for mitigation risks, prevention of catastrophic failures, and restoration of degraded systems, with broad applications in social science, engineering, and biology.
The recent rise of EEG-based end-to-end deep learning models presents a significant challenge in elucidating how these models process raw EEG signals and generate predictions in the frequency domain. This challenge limits the transparency and credibility of EEG-based end-to-end models, hindering their application in security-sensitive areas. To address this issue, we propose a mask perturbation method to explain the behavior of end-to-end models in the frequency domain. Considering the characteristics of EEG data, we introduce a target alignment loss to mitigate the out-of-distribution problem associated with perturbation operations. Additionally, we develop a perturbation generator to define perturbation generation in the frequency domain. Our explanation method is validated through experiments on multiple representative end-to-end deep learning models in the EEG decoding field, using an established EEG benchmark dataset. The results demonstrate the effectiveness and superiority of our method, and highlight its potential to advance research in EEG-based end-to-end models.
Deep learning model design, development, and debugging is a process driven by best practices, guidelines, trial-and-error, and the personal experiences of model developers. At multiple stages of this process, performance and internal model data can be logged and made available. However, due to the sheer complexity and scale of this data and process, model developers often resort to evaluating their model performance based on abstract metrics like accuracy and loss. We argue that a structured analysis of data along the model's architecture and at multiple abstraction levels can considerably streamline the debugging process. Such a systematic analysis can further connect the developer's design choices to their impacts on the model behavior, facilitating the understanding, diagnosis, and refinement of deep learning models. Hence, in this paper, we (1) contribute a conceptual framework structuring the data space of deep learning experiments. Our framework, grounded in literature analysis and requirements interviews, captures design dimensions and proposes mechanisms to make this data explorable and tractable. To operationalize our framework in a ready-to-use application, we (2) present the iNNspector system. iNNspector enables tracking of deep learning experiments and provides interactive visualizations of the data on all levels of abstraction from multiple models to individual neurons. Finally, we (3) evaluate our approach with three real-world use-cases and a user study with deep learning developers and data analysts, proving its effectiveness and usability.
Ellipsometry is used to indirectly measure the optical properties and thickness of thin films. However, solving the inverse problem of ellipsometry is time-consuming since it involves human expertise to apply the data fitting techniques. Many studies use traditional machine learning-based methods to model the complex mathematical fitting process. In our work, we approach this problem from a deep learning perspective. First, we introduce a large-scale benchmark dataset to facilitate deep learning methods. The proposed dataset encompasses 98 types of thin film materials and 4 types of substrate materials, including metals, alloys, compounds, and polymers, among others. Additionally, we propose a deep learning framework that leverages residual connections and self-attention mechanisms to learn the massive data points. We also introduce a reconstruction loss to address the common challenge of multiple solutions in thin film thickness prediction. Compared to traditional machine learning methods, our framework achieves state-of-the-art (SOTA) performance on our proposed dataset. The dataset and code will be available upon acceptance.
We present the first application of modern Hopfield networks to the problem of portfolio optimization. We performed an extensive study based on combinatorial purged cross-validation over several datasets and compared our results to both traditional and deep-learning-based methods for portfolio selection. Compared to state-of-the-art deep-learning methods such as Long-Short Term Memory networks and Transformers, we find that the proposed approach performs on par or better, while providing faster training times and better stability. Our results show that Modern Hopfield Networks represent a promising approach to portfolio optimization, allowing for an efficient, scalable, and robust solution for asset allocation, risk management, and dynamic rebalancing.
Epitope identification is vital for antibody design yet challenging due to the inherent variability in antibodies. While many deep learning methods have been developed for general protein binding site prediction tasks, whether they work for epitope prediction remains an understudied research question. The challenge is also heightened by the lack of a consistent evaluation pipeline with sufficient dataset size and epitope diversity. We introduce a filtered antibody-antigen complex structure dataset, AsEP (Antibody-specific Epitope Prediction). AsEP is the largest of its kind and provides clustered epitope groups, allowing the community to develop and test novel epitope prediction methods and evaluate their generalisability. AsEP comes with an easy-to-use interface in Python and pre-built graph representations of each antibody-antigen complex while also supporting customizable embedding methods. Using this new dataset, we benchmark several representative general protein-binding site prediction methods and find that their performances fall short of expectations for epitope prediction. To address this, we propose a novel method, WALLE, which leverages both unstructured modeling from protein language models and structural modeling from graph neural networks. WALLE demonstrate up to 3-10X performance improvement over the baseline methods. Our empirical findings suggest that epitope prediction benefits from combining sequential features provided by language models with geometrical information from graph representations. This provides a guideline for future epitope prediction method design. In addition, we reformulate the task as bipartite link prediction, allowing convenient model performance attribution and interpretability. We open source our data and code at https://github.com/biochunan/AsEP-dataset.
Recent advancements in computer vision have significantly improved image analysis tasks. Yet, deep learning models often struggle when applied to domains outside their training distribution, such as in geosciences, where domain-specific data can be scarce. This study investigates the classification, segmentation, and interpretability of CT-scan images of rock samples, focusing on the application of modern computer vision techniques to geoscientific tasks. We compare a range of segmentation methods to assess their efficacy, efficiency, and adaptability in geological image analysis. The methods evaluated include Otsu thresholding, clustering techniques (K-means, fuzzy C-means), a supervised machine learning approach (Random Forest), and deep learning models (UNet, ResNet152, and DINOv2), using ten binary sandstone datasets and three multi-class calcite datasets. DINOv2 was selected for its promising results in feature extraction and its potential applicability in geoscientific tasks, prompting further assessment of its interpretability and effectiveness in processing CT-scanned rock data. For classification, a non-fine-tuned DINOv2 demonstrates strong performance in classifying rock images, even when the CT-scans are outside its original training set. In segmentation tasks, thresholding and clustering techniques, though computationally efficient, produce subpar results despite preprocessing efforts. In contrast, supervised methods achieve better performance. While deep learning methods demand greater computational resources, they require minimal intervention and offer superior generalization. A LoRA fine-tuned DINOv2, in particular, excels in out-of-distribution segmentation and outperforms other methods in multi-class tasks, even with limited data. Notably, the segmentation masks generated by DINOv2 often appear more accurate than the original targets, based on visual inspection.
The electrocardiogram (ECG) is one of the most commonly-used tools to diagnose cardiovascular disease in clinical practice. Although deep learning models have achieved very impressive success in the field of automatic ECG analysis, they often lack model interpretability that is significantly important in the healthcare applications. To this end, many schemes such as general-purpose attention mechanism, Grad-CAM technique and ECG knowledge graph were proposed to be integrated with deep learning models. However, they either result in decreased classification performance or do not consist with the one in cardiologists' mind when interpreting ECG. In this study, we propose a novel disease-specific attention-based deep learning model (DANet) for arrhythmia detection from short ECG recordings. The novel idea is to introduce a soft-coding or hard-coding waveform enhanced module into existing deep neural networks, which amends original ECG signals with the guidance of the rule for diagnosis of a given disease type before being fed into the classification module. For the soft-coding DANet, we also develop a learning framework combining self-supervised pre-training with two-stage supervised training. To verify the effectiveness of our proposed DANet, we applied it to the problem of atrial premature contraction detection and the experimental results shows that it demonstrates superior performance compared to the benchmark model. Moreover, it also provides the waveform regions that deserve special attention in the model's decision-making process, allowing it to be a medical diagnostic assistant for physicians.
Deep learning-based fingerprinting is one of the current promising technologies for outdoor localization in cellular networks. However, deploying such localization systems for heterogeneous phones affects their accuracy as the cellular received signal strength (RSS) readings vary for different types of phones. In this paper, we introduce a number of techniques for addressing the phones heterogeneity problem in the deep-learning based localization systems. The basic idea is either to approximate a function that maps the cellular RSS measurements between different devices or to transfer the knowledge across them. Evaluation of the proposed techniques using different Android phones on four independent testbeds shows that our techniques can improve the localization accuracy by more than 220% for the four testbeds as compared to the state-of-the-art systems. This highlights the promise of the proposed device heterogeneity handling techniques for enabling a wide deployment of deep learning-based localization systems over different devices.
Most of the intrusion detection methods in computer networks are based on traffic flow characteristics. However, this approach may not fully exploit the potential of deep learning algorithms to directly extract features and patterns from raw packets. Moreover, it impedes real-time monitoring due to the necessity of waiting for the processing pipeline to complete and introduces dependencies on additional software components. In this paper, we investigate deep learning methodologies capable of detecting attacks in real-time directly from raw packet data within network traffic. We propose a novel approach where packets are stacked into windows and separately recognised, with a 2D image representation suitable for processing with computer vision models. Our investigation utilizes the CIC IDS-2017 dataset, which includes both benign traffic and prevalent real-world attacks, providing a comprehensive foundation for our research.
Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production on low compute devices. An increase in the number of connected devices around the world warrants compressed models that can be easily deployed at the local devices with low compute capacity and power accessibility. A wide range of solutions have been proposed by different researchers to reduce the size and complexity of such models, prominent among them are, Weight Quantization, Parameter Pruning, Network Pruning, low-rank representation, weights sharing, neural architecture search, knowledge distillation etc. In this research work, we investigate the performance impacts on various trained deep learning models, compressed using quantization and pruning techniques. We implemented both, quantization and pruning, compression techniques on popular deep learning models used in the image classification, object detection, language models and generative models-based problem statements. We also explored performance of various large language models (LLMs) after quantization and low rank adaptation. We used the standard evaluation metrics (model's size, accuracy, and inference time) for all the related problem statements and concluded this paper by discussing the challenges and future work.
In recent years, climate extremes such as floods have created significant environmental and economic hazards for Australia. Deep learning methods have been promising for predicting extreme climate events; however, large flooding events present a critical challenge due to factors such as model calibration and missing data. We present an ensemble quantile-based deep learning framework that addresses large-scale streamflow forecasts using quantile regression for uncertainty projections in prediction. We evaluate selected univariate and multivariate deep learning models and catchment strategies. Furthermore, we implement a multistep time-series prediction model using the CAMELS dataset for selected catchments across Australia. The ensemble model employs a set of quantile deep learning models for streamflow determined by historical streamflow data. We utilise the streamflow prediction and obtain flood probability using flood frequency analysis and compare it with historical flooding events for selected catchments. Our results demonstrate notable efficacy and uncertainties in streamflow forecasts with varied catchment properties. Our flood probability estimates show good accuracy in capturing the historical floods from the selected catchments. This underscores the potential for our deep learning framework to revolutionise flood forecasting across diverse regions and be implemented as an early warning system.
Pancreas segmentation has been traditionally challenging due to its small size in computed tomography abdominal volumes, high variability of shape and positions among patients, and blurred boundaries due to low contrast between the pancreas and surrounding organs. Many deep learning models for pancreas segmentation have been proposed in the past few years. We present a thorough systematic review based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) statement. The literature search was conducted on PubMed, Web of Science, Scopus, and IEEE Xplore on original studies published in peer-reviewed journals from 2013 to 2023. Overall, 130 studies were retrieved. We initially provided an overview of the technical background of the most common network architectures and publicly available datasets. Then, the analysis of the studies combining visual presentation in tabular form and text description was reported. The tables grouped the studies specifying the application, dataset size, design (model architecture, learning strategy, and loss function), results, and main contributions. We first analyzed the studies focusing on parenchyma segmentation using coarse-to-fine approaches, multi-organ segmentation, semi-supervised learning, and unsupervised learning, followed by those studies on generalization to other datasets and those concerning the design of new loss functions. Then, we analyzed the studies on segmentation of tumors, cysts, and inflammation reporting multi-stage methods, semi-supervised learning, generalization to other datasets, and design of new loss functions. Finally, we provided a critical discussion on the subject based on the published evidence underlining current issues that need to be addressed before clinical translation.
Nowadays, deep learning models are increasingly required to be both interpretable and highly accurate. We present an approach that integrates Kolmogorov-Arnold Network (KAN) classification heads and Fuzzy Pooling into convolutional neural networks (CNNs). By utilizing the interpretability of KAN and the uncertainty handling capabilities of fuzzy logic, the integration shows potential for improved performance in image classification tasks. Our comparative analysis demonstrates that the modified CNN architecture with KAN and Fuzzy Pooling achieves comparable or higher accuracy than traditional models. The findings highlight the effectiveness of combining fuzzy logic and KAN to develop more interpretable and efficient deep learning models. Future work will aim to expand this approach across larger datasets.
While complex simulations of physical systems have been widely used in engineering and scientific computing, lowering their often prohibitive computational requirements has only recently been tackled by deep learning approaches. In this paper, we present GraphSplineNets, a novel deep-learning method to speed up the forecasting of physical systems by reducing the grid size and number of iteration steps of deep surrogate models. Our method uses two differentiable orthogonal spline collocation methods to efficiently predict response at any location in time and space. Additionally, we introduce an adaptive collocation strategy in space to prioritize sampling from the most important regions. GraphSplineNets improve the accuracy-speedup tradeoff in forecasting various dynamical systems with increasing complexity, including the heat equation, damped wave propagation, Navier-Stokes equations, and real-world ocean currents in both regular and irregular domains.