Authors: Anissa Alloula, Rima Mustafa, Daniel R McGowan, Bart{\l}omiej W. Papie\.z
Abstract: Recent work has uncovered alarming disparities in the performance of machine learning models in healthcare. In this study, we explore whether such disparities are present in the UK Biobank fundus retinal images by training and evaluating a disease classification model on these images. We assess possible disparities across various population groups and find substantial differences despite strong overall performance of the model. In particular, we discover unfair performance for certain assessment centres, which is surprising given the rigorous data standardisation protocol. We compare how these differences emerge and apply a range of existing bias mitigation methods to each one. A key insight is that each disparity has unique properties and responds differently to the mitigation methods. We also find that these methods are largely unable to enhance fairness, highlighting the need for better bias mitigation methods tailored to the specific type of bias.
Authors: Mohsen Amoei, Dan Poenaru
Abstract: This study proposes a novel, integrative framework for patient-centered data science in the digital health era. We developed a multidimensional model that combines traditional clinical data with patient-reported outcomes, social determinants of health, and multi-omic data to create comprehensive digital patient representations. Our framework employs a multi-agent artificial intelligence approach, utilizing various machine learning techniques including large language models, to analyze complex, longitudinal datasets. The model aims to optimize multiple patient outcomes simultaneously while addressing biases and ensuring generalizability. We demonstrate how this framework can be implemented to create a learning healthcare system that continuously refines strategies for optimal patient care. This approach has the potential to significantly improve the translation of digital health innovations into real-world clinical benefits, addressing current limitations in AI-driven healthcare models.
Authors: Wen-Liang Hwang
Abstract: In large-scale learning algorithms, the momentum term is usually included in the stochastic sub-gradient method to improve the learning speed because it can navigate ravines efficiently to reach a local minimum. However, step-size and momentum weight hyper-parameters must be appropriately tuned to optimize convergence. We thus analyze the convergence rate using stochastic programming with Polyak's acceleration of two commonly used step-size learning rates: ``diminishing-to-zero" and ``constant-and-drop" (where the sequence is divided into stages and a constant step-size is applied at each stage) under strongly convex functions over a compact convex set with bounded sub-gradients. For the former, we show that the convergence rate can be written as a product of exponential in step-size and polynomial in momentum weight. Our analysis justifies the convergence of using the default momentum weight setting and the diminishing-to-zero step-size sequence in large-scale machine learning software. For the latter, we present the condition for the momentum weight sequence to converge at each stage.
Authors: Mengjie Fan, Jinlu Yu, Daniel Weiskopf, Nan Cao, Huai-Yu Wang, Liang Zhou
Abstract: We introduce a visual analysis method for multiple causal graphs with different outcome variables, namely, multi-outcome causal graphs. Multi-outcome causal graphs are important in healthcare for understanding multimorbidity and comorbidity. To support the visual analysis, we collaborated with medical experts to devise two comparative visualization techniques at different stages of the analysis process. First, a progressive visualization method is proposed for comparing multiple state-of-the-art causal discovery algorithms. The method can handle mixed-type datasets comprising both continuous and categorical variables and assist in the creation of a fine-tuned causal graph of a single outcome. Second, a comparative graph layout technique and specialized visual encodings are devised for the quick comparison of multiple causal graphs. In our visual analysis approach, analysts start by building individual causal graphs for each outcome variable, and then, multi-outcome causal graphs are generated and visualized with our comparative technique for analyzing differences and commonalities of these causal graphs. Evaluation includes quantitative measurements on benchmark datasets, a case study with a medical expert, and expert user studies with real-world health research data.
Authors: Sai Balaji, Christopher Sun, Anaiy Somalwar
Abstract: The early and accurate diagnosis of sepsis is critical for enhancing patient outcomes. This study aims to use heart rate variability (HRV) features to develop an effective predictive model for sepsis detection. Critical HRV features are identified through feature engineering methods, including statistical bootstrapping and the Boruta algorithm, after which XGBoost and Random Forest classifiers are trained with differential hyperparameter settings. In addition, ensemble models are constructed to pool the prediction probabilities of high-recall and high-precision classifiers and improve model performance. Finally, a neural network model is trained on the HRV features, achieving an F1 score of 0.805, a precision of 0.851, and a recall of 0.763. The best-performing machine learning model is compared to this neural network through an interpretability analysis, where Local Interpretable Model-agnostic Explanations are implemented to determine decision-making criterion based on numerical ranges and thresholds for specific features. This study not only highlights the efficacy of HRV in automated sepsis diagnosis but also increases the transparency of black box outputs, maximizing clinical applicability.
Authors: Guanchao Feng, Dhruv Desai, Stefano Pasquali, Dhagash Mehta
Abstract: In many real-world classification or recognition tasks, it is often difficult to collect training examples that exhaust all possible classes due to, for example, incomplete knowledge during training or ever changing regimes. Therefore, samples from unknown/novel classes may be encountered in testing/deployment. In such scenarios, the classifiers should be able to i) perform classification on known classes, and at the same time, ii) identify samples from unknown classes. This is known as open-set recognition. Although random forest has been an extremely successful framework as a general-purpose classification (and regression) method, in practice, it usually operates under the closed-set assumption and is not able to identify samples from new classes when run out of the box. In this work, we propose a novel approach to enabling open-set recognition capability for random forest classifiers by incorporating distance metric learning and distance-based open-set recognition. The proposed method is validated on both synthetic and real-world datasets. The experimental results indicate that the proposed approach outperforms state-of-the-art distance-based open-set recognition methods.
Authors: Pedro Freire, Egor Manuylovich, Jaroslaw E. Prilepsky, Sergei K. Turitsy
Abstract: This tutorial-review on applications of artificial neural networks in photonics targets a broad audience, ranging from optical research and engineering communities to computer science and applied mathematics. We focus here on the research areas at the interface between these disciplines, attempting to find the right balance between technical details specific to each domain and overall clarity. First, we briefly recall key properties and peculiarities of some core neural network types, which we believe are the most relevant to photonics, also linking the layer's theoretical design to some photonics hardware realizations. After that, we elucidate the question of how to fine-tune the selected model's design to perform the required task with optimized accuracy. Then, in the review part, we discuss recent developments and progress for several selected applications of neural networks in photonics, including multiple aspects relevant to optical communications, imaging, sensing, and the design of new materials and lasers. In the following section, we put a special emphasis on how to accurately evaluate the complexity of neural networks in the context of the transition from algorithms to hardware implementation. The introduced complexity characteristics are used to analyze the applications of neural networks in optical communications, as a specific, albeit highly important example, comparing those with some benchmark signal processing methods. We combine the description of the well-known model compression strategies used in machine learning, with some novel techniques introduced recently in optical applications of neural networks. It is important to stress that although our focus in this tutorial-review is on photonics, we believe that the methods and techniques presented here can be handy in a much wider range of scientific and engineering applications.
Authors: Valerio Guarrasi, Fatih Aksu, Camillo Maria Caruso, Francesco Di Feola, Aurora Rofena, Filippo Ruffini, Paolo Soda
Abstract: Deep learning has revolutionized biomedical research by providing sophisticated methods to handle complex, high-dimensional data. Multimodal deep learning (MDL) further enhances this capability by integrating diverse data types such as imaging, textual data, and genetic information, leading to more robust and accurate predictive models. In MDL, differently from early and late fusion methods, intermediate fusion stands out for its ability to effectively combine modality-specific features during the learning process. This systematic review aims to comprehensively analyze and formalize current intermediate fusion methods in biomedical applications. We investigate the techniques employed, the challenges faced, and potential future directions for advancing intermediate fusion methods. Additionally, we introduce a structured notation to enhance the understanding and application of these methods beyond the biomedical domain. Our findings are intended to support researchers, healthcare professionals, and the broader deep learning community in developing more sophisticated and insightful multimodal models. Through this review, we aim to provide a foundational framework for future research and practical applications in the dynamic field of MDL.
Authors: Benedikt Barthel Sorensen, Leonardo Zepeda-N\'u\~nez, Ignacio Lopez-Gomez, Zhong Yi Wan, Rob Carver, Fei Sha, Themistoklis Sapsis
Abstract: Chaotic systems, such as turbulent flows, are ubiquitous in science and engineering. However, their study remains a challenge due to the large range scales, and the strong interaction with other, often not fully understood, physics. As a consequence, the spatiotemporal resolution required for accurate simulation of these systems is typically computationally infeasible, particularly for applications of long-term risk assessment, such as the quantification of extreme weather risk due to climate change. While data-driven modeling offers some promise of alleviating these obstacles, the scarcity of high-quality simulations results in limited available data to train such models, which is often compounded by the lack of stability for long-horizon simulations. As such, the computational, algorithmic, and data restrictions generally imply that the probability of rare extreme events is not accurately captured. In this work we present a general strategy for training neural network models to non-intrusively correct under-resolved long-time simulations of chaotic systems. The approach is based on training a post-processing correction operator on under-resolved simulations nudged towards a high-fidelity reference. This enables us to learn the dynamics of the underlying system directly, which allows us to use very little training data, even when the statistics thereof are far from converged. Additionally, through the use of probabilistic network architectures we are able to leverage the uncertainty due to the limited training data to further improve extrapolation capabilities. We apply our framework to severely under-resolved simulations of quasi-geostrophic flow and demonstrate its ability to accurately predict the anisotropic statistics over time horizons more than 30 times longer than the data seen in training.
Authors: Zibo Liu, Zhe Jiang, Zelin Xu, Tingsong Xiao, Zhengkun Xiao, Haibo Wang, Shigang Chen
Abstract: Traffic forecasting uses recent measurements by sensors installed at chosen locations to forecast the future road traffic. Existing work either assumes all locations are equipped with sensors or focuses on short-term forecast. This paper studies partial sensing traffic forecast of long-term traffic, assuming sensors only at some locations. The study is important in lowering the infrastructure investment cost in traffic management since deploying sensors at all locations could incur prohibitively high cost. However, the problem is challenging due to the unknown distribution at unsensed locations, the intricate spatio-temporal correlation in long-term forecasting, as well as noise in data and irregularities in traffic patterns (e.g., road closure). We propose a Spatio-Temporal Partial Sensing (STPS) forecast model for long-term traffic prediction, with several novel contributions, including a rank-based embedding technique to capture irregularities and overcome noise, a spatial transfer matrix to overcome the spatial distribution shift from permanently sensed locations to unsensed locations, and a multi-step training process that utilizes all available data to successively refine the model parameters for better accuracy. Extensive experiments on several real-world traffic datasets demonstrate that STPS outperforms the state-of-the-art and achieves superior accuracy in partial sensing long-term forecasting.
Authors: Chu Zhao, Enneng Yang, Yuliang Liang, Jianzhe Zhao, Guibing Guo, Xingwei Wang
Abstract: Graph Contrastive Learning (GCL) leverages data augmentation techniques to produce contrasting views, enhancing the accuracy of recommendation systems through learning the consistency between contrastive views. However, existing augmentation methods, such as directly perturbing interaction graph (e.g., node/edge dropout), may interfere with the original connections and generate poor contrasting views, resulting in sub-optimal performance. In this paper, we define the views that share only a small amount of information with the original graph due to poor data augmentation as noisy views (i.e., the last 20% of the views with a cosine similarity value less than 0.1 to the original view). We demonstrate through detailed experiments that noisy views will significantly degrade recommendation performance. Further, we propose a model-agnostic Symmetric Graph Contrastive Learning (SGCL) method with theoretical guarantees to address this issue. Specifically, we introduce symmetry theory into graph contrastive learning, based on which we propose a symmetric form and contrast loss resistant to noisy interference. We provide theoretical proof that our proposed SGCL method has a high tolerance to noisy views. Further demonstration is given by conducting extensive experiments on three real-world datasets. The experimental results demonstrate that our approach substantially increases recommendation accuracy, with relative improvements reaching as high as 12.25% over nine other competing models. These results highlight the efficacy of our method.
Authors: Akram Elghouat, Ahmed Algouti, Abdellah Algouti, Soukaina Baid
Abstract: Effective flood hazard management requires evaluating and predicting flash flood susceptibility. Convolutional neural networks (CNNs) are commonly used for this task but face issues like gradient explosion and overfitting. This study explores the use of an attention mechanism, specifically the convolutional block attention module (CBAM), to enhance CNN models for flash flood susceptibility in the ungauged Rheraya watershed, a flood prone region. We used ResNet18, DenseNet121, and Xception as backbone architectures, integrating CBAM at different locations. Our dataset included 16 conditioning factors and 522 flash flood inventory points. Performance was evaluated using accuracy, precision, recall, F1-score, and the area under the curve (AUC) of the receiver operating characteristic (ROC). Results showed that CBAM significantly improved model performance, with DenseNet121 incorporating CBAM in each convolutional block achieving the best results (accuracy = 0.95, AUC = 0.98). Distance to river and drainage density were identified as key factors. These findings demonstrate the effectiveness of the attention mechanism in improving flash flood susceptibility modeling and offer valuable insights for disaster management.
Authors: Tianqi Wang, Shubham Singh
Abstract: Inspired by recent advances in Kolmogorov-Arnold Networks (KANs), we introduce a novel approach to latent factor conditional asset pricing models. While previous machine learning applications in asset pricing have predominantly used Multilayer Perceptrons with ReLU activation functions to model latent factor exposures, our method introduces a KAN-based autoencoder which surpasses MLP models in both accuracy and interpretability. Our model offers enhanced flexibility in approximating exposures as nonlinear functions of asset characteristics, while simultaneously providing users with an intuitive framework for interpreting latent factors. Empirical backtesting demonstrates our model's superior ability to explain cross-sectional risk exposures. Moreover, long-short portfolios constructed using our model's predictions achieve higher Sharpe ratios, highlighting its practical value in investment management.
Authors: Shaoxu Cheng, Kanglei Geng, Chiyuan He, Zihuan Qiu, Linfeng Xu, Heqian Qiu, Lanxiao Wang, Qingbo Wu, Fanman Meng, Hongliang Li
Abstract: Continual Learning (CL) aims to enable Deep Neural Networks (DNNs) to learn new data without forgetting previously learned knowledge. The key to achieving this goal is to avoid confusion at the feature level, i.e., avoiding confusion within old tasks and between new and old tasks. Previous prototype-based CL methods generate pseudo features for old knowledge replay by adding Gaussian noise to the centroids of old classes. However, the distribution in the feature space exhibits anisotropy during the incremental process, which prevents the pseudo features from faithfully reproducing the distribution of old knowledge in the feature space, leading to confusion in classification boundaries within old tasks. To address this issue, we propose the Distribution-Level Memory Recall (DMR) method, which uses a Gaussian mixture model to precisely fit the feature distribution of old knowledge at the distribution level and generate pseudo features in the next stage. Furthermore, resistance to confusion at the distribution level is also crucial for multimodal learning, as the problem of multimodal imbalance results in significant differences in feature responses between different modalities, exacerbating confusion within old tasks in prototype-based CL methods. Therefore, we mitigate the multi-modal imbalance problem by using the Inter-modal Guidance and Intra-modal Mining (IGIM) method to guide weaker modalities with prior information from dominant modalities and further explore useful information within modalities. For the second key, We propose the Confusion Index to quantitatively describe a model's ability to distinguish between new and old tasks, and we use the Incremental Mixup Feature Enhancement (IMFE) method to enhance pseudo features with new sample features, alleviating classification confusion between new and old knowledge.
Authors: Taeyoung Kim, Myungjoo Kang
Abstract: The Rectified Power Unit (RePU) activation functions, unlike the Rectified Linear Unit (ReLU), have the advantage of being a differentiable function when constructing neural networks. However, it can be experimentally observed when deep layers are stacked, neural networks constructed with RePU encounter critical issues. These issues include the values exploding or vanishing and failure of training. And these happen regardless of the hyperparameter initialization. From the perspective of effective theory, we aim to identify the causes of this phenomenon and propose a new activation function that retains the advantages of RePU while overcoming its drawbacks.
Authors: Mohammad Sadegh Eshaghi, Mostafa Bamdad, Cosmin Anitescu, Yizheng Wang, Xiaoying Zhuang, Timon Rabczuk
Abstract: This study investigates different Scientific Machine Learning (SciML) approaches for the analysis of functionally graded (FG) porous beams and compares them under a new framework. The beam material properties are assumed to vary as an arbitrary continuous function. The methods consider the output of a neural network/operator as an approximation to the displacement fields and derive the equations governing beam behavior based on the continuum formulation. The methods are implemented in the framework and formulated by three approaches: (a) the vector approach leads to a Physics-Informed Neural Network (PINN), (b) the energy approach brings about the Deep Energy Method (DEM), and (c) the data-driven approach, which results in a class of Neural Operator methods. Finally, a neural operator has been trained to predict the response of the porous beam with functionally graded material under any porosity distribution pattern and any arbitrary traction condition. The results are validated with analytical and numerical reference solutions. The data and code accompanying this manuscript will be publicly available at https://github.com/eshaghi-ms/DeepNetBeam.
Authors: Ling Wang, Yixiang Huang, Hao Wu
Abstract: Dynamic graphs (DG) are often used to describe evolving interactions between nodes in real-world applications. Temporal patterns are a natural feature of DGs and are also key to representation learning. However, existing dynamic GCN models are mostly composed of static GCNs and sequence modules, which results in the separation of spatiotemporal information and cannot effectively capture complex temporal patterns in DGs. To address this problem, this study proposes a spatial-temporal graph convolutional networks with diversified transformation (STGCNDT), which includes three aspects: a) constructing a unified graph tensor convolutional network (GTCN) using tensor M-products without the need to represent spatiotemporal information separately; b) introducing three transformation schemes in GTCN to model complex temporal patterns to aggregate temporal information; and c) constructing an ensemble of diversified transformation schemes to obtain higher representation capabilities. Empirical studies on four DGs that appear in communication networks show that the proposed STGCNDT significantly outperforms state-of-the-art models in solving link weight estimation tasks due to the diversified transformations.
Authors: Longlong Lin, Yunfeng Yu, Zihao Wang, Zeli Wang, Yuying Zhao, Jin Zhao, Tao Jia
Abstract: Network embedding has numerous practical applications and has received extensive attention in graph learning, which aims at mapping vertices into a low-dimensional and continuous dense vector space by preserving the underlying structural properties of the graph. Many network embedding methods have been proposed, among which factorization of the Personalized PageRank (PPR for short) matrix has been empirically and theoretically well supported recently. However, several fundamental issues cannot be addressed. (1) Existing methods invoke a seminal Local Push subroutine to approximate \textit{a single} row or column of the PPR matrix. Thus, they have to execute $n$ ($n$ is the number of nodes) Local Push subroutines to obtain a provable PPR matrix, resulting in prohibitively high computational costs for large $n$. (2) The PPR matrix has limited power in capturing the structural similarity between vertices, leading to performance degradation. To overcome these dilemmas, we propose PSNE, an efficient spectral s\textbf{P}arsification method for \textbf{S}caling \textbf{N}etwork \textbf{E}mbedding, which can fast obtain the embedding vectors that retain strong structural similarities. Specifically, PSNE first designs a matrix polynomial sparser to accelerate the calculation of the PPR matrix, which has a theoretical guarantee in terms of the Frobenius norm. Subsequently, PSNE proposes a simple but effective multiple-perspective strategy to enhance further the representation power of the obtained approximate PPR matrix. Finally, PSNE applies a randomized singular value decomposition algorithm on the sparse and multiple-perspective PPR matrix to get the target embedding vectors. Experimental evaluation of real-world and synthetic datasets shows that our solutions are indeed more efficient, effective, and scalable compared with ten competitors.
Authors: Masoud Muhammed Hassan
Abstract: Because of its strong predictive skills, deep learning has emerged as an essential tool in many industries, including healthcare. Traditional deep learning models, on the other hand, frequently lack interpretability and omit to take prediction uncertainty into account two crucial components of clinical decision making. In order to produce explainable and uncertainty aware predictions, this study presents a novel framework called Bayesian Kolmogorov Arnold Networks (BKANs), which combines the expressive capacity of Kolmogorov Arnold Networks with Bayesian inference. We employ BKANs on two medical datasets, which are widely used benchmarks for assessing machine learning models in medical diagnostics: the Pima Indians Diabetes dataset and the Cleveland Heart Disease dataset. Our method provides useful insights into prediction confidence and decision boundaries and outperforms traditional deep learning models in terms of prediction accuracy. Moreover, BKANs' capacity to represent aleatoric and epistemic uncertainty guarantees doctors receive more solid and trustworthy decision support. Our Bayesian strategy improves the interpretability of the model and considerably minimises overfitting, which is important for tiny and imbalanced medical datasets, according to experimental results. We present possible expansions to further use BKANs in more complicated multimodal datasets and address the significance of these discoveries for future research in building reliable AI systems for healthcare. This work paves the way for a new paradigm in deep learning model deployment in vital sectors where transparency and reliability are crucial.
Authors: Ali Shaban, Heiko Paulheim
Abstract: Snapshot ensembles have been widely used in various fields of prediction. They allow for training an ensemble of prediction models at the cost of training a single one. They are known to yield more robust predictions by creating a set of diverse base models. In this paper, we introduce an approach to transfer the idea of snapshot ensembles to link prediction models in knowledge graphs. Moreover, since link prediction in knowledge graphs is a setup without explicit negative examples, we propose a novel training loop that iteratively creates negative examples using previous snapshot models. An evaluation with four base models across four datasets shows that this approach constantly outperforms the single model approach, while keeping the training time constant.
Authors: Weifeng Xu, Xiang Zhu, Xiaoyong Li
Abstract: The conditional diffusion model (CDM) enhances the standard diffusion model by providing more control, improving the quality and relevance of the outputs, and making the model adaptable to a wider range of complex tasks. However, inaccurate conditional inputs in the inverse process of CDM can easily lead to generating fixed errors in the neural network, which diminishes the adaptability of a well-trained model. The existing methods like data augmentation, adversarial training, robust optimization can improve the robustness, while they often face challenges such as high computational complexity, limited applicability to unknown perturbations, and increased training difficulty. In this paper, we propose a lightweight solution, the Robust Conditional Diffusion Model (RCDM), based on control theory to dynamically reduce the impact of noise and significantly enhance the model's robustness. RCDM leverages the collaborative interaction between two neural networks, along with optimal control strategies derived from control theory, to optimize the weights of two networks during the sampling process. Unlike conventional techniques, RCDM establishes a mathematical relationship between fixed errors and the weights of the two neural networks without incurring additional computational overhead. Extensive experiments were conducted on MNIST and CIFAR-10 datasets, and the results demonstrate the effectiveness and adaptability of our proposed model.
Authors: Dongwei Xu, Jiajun Chen, Yao Lu, Tianhao Xia, Qi Xuan, Wei Wang, Yun Lin, Xiaoniu Yang
Abstract: Recently, deep learning technology has been successfully introduced into Automatic Modulation Recognition (AMR) tasks. However, the success of deep learning is all attributed to the training on large-scale datasets. Such a large amount of data brings huge pressure on storage, transmission and model training. In order to solve the problem of large amount of data, some researchers put forward the method of data distillation, which aims to compress large training data into smaller synthetic datasets to maintain its performance. While numerous data distillation techniques have been developed within the realm of image processing, the unique characteristics of signals set them apart. Signals exhibit distinct features across various domains, necessitating specialized approaches for their analysis and processing. To this end, a novel dataset distillation method--Multi-domain Distribution Matching (MDM) is proposed. MDM employs the Discrete Fourier Transform (DFT) to translate timedomain signals into the frequency domain, and then uses a model to compute distribution matching losses between the synthetic and real datasets, considering both the time and frequency domains. Ultimately, these two losses are integrated to update the synthetic dataset. We conduct extensive experiments on three AMR datasets. Experimental results show that, compared with baseline methods, our method achieves better performance under the same compression ratio. Furthermore, we conduct crossarchitecture generalization experiments on several models, and the experimental results show that our synthetic datasets can generalize well on other unseen models.
Authors: Jiawei Zhou
Abstract: Tornadoes are among the most intense atmospheric vortex phenomena and pose significant challenges for detection and forecasting. Conventional methods, which heavily depend on ground-based observations and radar data, are limited by issues such as decreased accuracy over greater distances and a high rate of false positives. To address these challenges, this study utilizes the Seamless Hybrid Scan Reflectivity (SHSR) dataset from the Multi-Radar Multi-Sensor (MRMS) system, which integrates data from multiple radar sources to enhance accuracy. A novel hybrid model, the Kalman-Convolutional BiLSTM with Multi-Head Attention, is introduced to improve dynamic state estimation and capture both spatial and temporal dependencies within the data. This model demonstrates superior performance in precision, recall, F1-Score, and accuracy compared to methods such as K-Nearest Neighbors (KNN) and LightGBM. The results highlight the considerable potential of advanced machine learning techniques to improve tornado prediction and reduce false alarm rates. Future research will focus on expanding datasets, exploring innovative model architectures, and incorporating large language models (LLMs) to provide deeper insights. This research introduces a novel model for tornado prediction, offering a robust framework for enhancing forecasting accuracy and public safety.
Authors: Adri\`a Solana, Erik Frans\'en, Gonzalo Uribarri
Abstract: Multivariate Time Series Classification (MTSC) is a ubiquitous problem in science and engineering, particularly in neuroscience, where most data acquisition modalities involve the simultaneous time-dependent recording of brain activity in multiple brain regions. In recent years, Random Convolutional Kernel models such as ROCKET and MiniRocket have emerged as highly effective time series classification algorithms, capable of achieving state-of-the-art accuracy results with low computational load. Despite their success, these types of models face two major challenges when employed in neuroscience: 1) they struggle to deal with high-dimensional data such as EEG and MEG, and 2) they are difficult to interpret. In this work, we present a novel ROCKET-based algorithm, named Detach-Rocket Ensemble, that is specifically designed to address these two problems in MTSC. Our algorithm leverages pruning to provide an integrated estimation of channel importance, and ensembles to achieve better accuracy and provide a label probability. Using a synthetic multivariate time series classification dataset in which we control the amount of information carried by each of the channels, we first show that our algorithm is able to correctly recover the channel importance for classification. Then, using two real-world datasets, a MEG dataset and an EEG dataset, we show that Detach-Rocket Ensemble is able to provide both interpretable channel relevance and competitive classification accuracy, even when applied directly to the raw brain data, without the need for feature engineering.
Authors: Kylen Solvik, Stephen G. Penny, Stephan Hoyer
Abstract: Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) data assimilation is often difficult to implement in practice due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton method can be applied by combining backpropagation of errors with Hessian approximation. This approach can be used with either a conventional numerical model implemented within a software framework that supports automatic differentiation, or a machine learning (ML) based surrogate model. We test the new approach on a variety of Lorenz-96 and quasi-geostrophic models. The results indicate potential for a deeper integration of modeling, data assimilation, and new technologies in a next-generation of operational forecast systems that leverage weather models designed to support automatic differentiation.
Authors: Zepeng Zhang, Olga Fink
Abstract: Detecting and localizing leakages is a significant challenge for the efficient and sustainable management of water distribution networks (WDN). Leveraging the inherent graph structure of WDNs, recent approaches have used graph-based data-driven methods. However, these methods often learn shortcuts that work well with in-distribution data but fail to generalize to out-of-distribution data. To address this limitation and inspired by the perfect generalization ability of classical algorithms, we propose an algorithm-informed graph neural network (AIGNN). Recognizing that WDNs function as flow networks, incorporating max-flow information can be beneficial for inferring pressures. In the proposed framework, we first train AIGNN to emulate the Ford-Fulkerson algorithm for solving max-flow problems. This algorithmic knowledge is then transferred to address the pressure estimation problem in WDNs. Two AIGNNs are deployed, one to reconstruct pressure based on the current measurements, and another to predict pressure based on previous measurements. Leakages are detected and localized by comparing the outputs of the reconstructor and the predictor. By pretraining AIGNNs to reason like algorithms, they are expected to extract more task-relevant and generalizable features. Experimental results demonstrate that the proposed algorithm-informed approach achieves superior results with better generalization ability compared to GNNs that do not incorporate algorithmic knowledge.
Authors: Lixin Shen, Rui Wang, Yuesheng Xu, Mingsong Yan
Abstract: Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the sparsity level of learned neural networks. We first derive the $\ell_1$-norm sparsity-promoting deep learning models including single and multiple regularization parameters models, from a statistical viewpoint. We then characterize the sparsity level of a regularized neural network in terms of the choice of the regularization parameters. Based on the characterizations, we develop iterative algorithms for selecting regularization parameters so that the weight parameters of the resulting deep neural network enjoy prescribed sparsity levels. Numerical experiments are presented to demonstrate the effectiveness of the proposed algorithms in choosing desirable regularization parameters and obtaining corresponding neural networks having both of predetermined sparsity levels and satisfactory approximation accuracy.
Authors: Aravinda Jatavallabha, Jacob Gerlach, Aadithya Naresh
Abstract: This research investigates flight delay trends by examining factors such as departure time, airline, and airport. It employs regression machine learning methods to predict the contributions of various sources to delays. Time-series models, including LSTM, Hybrid LSTM, and Bi-LSTM, are compared with baseline regression models such as Multiple Regression, Decision Tree Regression, Random Forest Regression, and Neural Network. Despite considerable errors in the baseline models, the study aims to identify influential features in delay prediction, potentially informing flight planning strategies. Unlike previous work, this research focuses on regression tasks and explores the use of time-series models for predicting flight delays. It offers insights into aviation operations by independently analyzing each delay component (e.g., security, weather).
Authors: Qilei Li, Ahmed M. Abdelmoniem
Abstract: Federated Learning (FL) is an emerging distributed machine learning paradigm that allows multiple clients to collaboratively train a global model without sharing private local data. However, FL systems are vulnerable to attacks from malicious clients, who can degrade the global model performance through data poisoning and model poisoning. Existing defense methods typically focus on a single type of attack, such as Byzantine attacks or backdoor attacks, and are often ineffective against potential data poisoning attacks like label flipping and label shuffling. Additionally, these methods often lack accuracy and robustness in detecting and handling malicious updates. To address these issues, we propose a novel method based on model confidence scores, which evaluates the uncertainty of client model updates to detect and defend against malicious clients. Our approach is comprehensively effective for both model poisoning and data poisoning attacks and is capable of accurately identifying and mitigating potential malicious updates from being aggregated. Experimental results demonstrate that our method significantly improves the robustness of FL systems against various types of attacks, also achieving higher model accuracy and stability across various scenarios.
Authors: Shaopeng Fu, Xuexue Sun, Ke Qing, Tianhang Zheng, Di Wang
Abstract: Though pre-trained encoders can be easily accessed online to build downstream machine learning (ML) services quickly, various attacks have been designed to compromise the security and privacy of these encoders. While most attacks target encoders on the upstream side, it remains unknown how an encoder could be threatened when deployed in a downstream ML service. This paper unveils a new vulnerability: the Pre-trained Encoder Inference (PEI) attack, which posts privacy threats toward encoders hidden behind downstream ML services. By only providing API accesses to a targeted downstream service and a set of candidate encoders, the PEI attack can infer which encoder is secretly used by the targeted service based on candidate ones. We evaluate the attack performance of PEI against real-world encoders on three downstream tasks: image classification, text classification, and text-to-image generation. Experiments show that the PEI attack succeeds in revealing the hidden encoder in most cases and seldom makes mistakes even when the hidden encoder is not in the candidate set. We also conducted a case study on one of the most recent vision-language models, LLaVA, to illustrate that the PEI attack is useful in assisting other ML attacks such as adversarial attacks. The code is available at https://github.com/fshp971/encoder-inference.
Authors: M. Sajid, A. Quadir, M. Tanveer
Abstract: The random vector functional link (RVFL) network is well-regarded for its strong generalization capabilities in the field of machine learning. However, its inherent dependencies on the square loss function make it susceptible to noise and outliers. Furthermore, the calculation of RVFL's unknown parameters necessitates matrix inversion of the entire training sample, which constrains its scalability. To address these challenges, we propose the Wave-RVFL, an RVFL model incorporating the wave loss function. We formulate and solve the proposed optimization problem of the Wave-RVFL using the adaptive moment estimation (Adam) algorithm in a way that successfully eliminates the requirement for matrix inversion and significantly enhances scalability. The Wave-RVFL exhibits robustness against noise and outliers by preventing over-penalization of deviations, thereby maintaining a balanced approach to managing noise and outliers. The proposed Wave-RVFL model is evaluated on multiple UCI datasets, both with and without the addition of noise and outliers, across various domains and sizes. Empirical results affirm the superior performance and robustness of the Wave-RVFL compared to baseline models, establishing it as a highly effective and scalable classification solution.
Authors: Eduardo Sanchez-Karhunen, Jose F. Quesada-Moreno, Miguel A. Guti\'errez-Naranjo
Abstract: Intent detection is a text classification task whose aim is to recognize and label the semantics behind a users query. It plays a critical role in various business applications. The output of the intent detection module strongly conditions the behavior of the whole system. This sequence analysis task is mainly tackled using deep learning techniques. Despite the widespread use of these techniques, the internal mechanisms used by networks to solve the problem are poorly understood. Recent lines of work have analyzed the computational mechanisms learned by RNNs from a dynamical systems perspective. In this work, we investigate how different RNN architectures solve the SNIPS intent detection problem. Sentences injected into trained networks can be interpreted as trajectories traversing a hidden state space. This space is constrained to a low-dimensional manifold whose dimensionality is related to the embedding and hidden layer sizes. To generate predictions, RNN steers the trajectories towards concrete regions, spatially aligned with the output layer matrix rows directions. Underlying the system dynamics, an unexpected fixed point topology has been identified with a limited number of attractors. Our results provide new insights into the inner workings of networks that solve the intent detection task.
Authors: Sina Tabakhi, Charlotte Vandermeulen, Ian Sudbery, Haiping Lu
Abstract: The increase in high-dimensional multiomics data demands advanced integration models to capture the complexity of human diseases. Graph-based deep learning integration models, despite their promise, struggle with small patient cohorts and high-dimensional features, often applying independent feature selection without modeling relationships among omics. Furthermore, conventional graph-based omics models focus on homogeneous graphs, lacking multiple types of nodes and edges to capture diverse structures. We introduce a Heterogeneous Graph ATtention network for omics integration (HeteroGATomics) to improve cancer diagnosis. HeteroGATomics performs joint feature selection through a multi-agent system, creating dedicated networks of feature and patient similarity for each omic modality. These networks are then combined into one heterogeneous graph for learning holistic omic-specific representations and integrating predictions across modalities. Experiments on three cancer multiomics datasets demonstrate HeteroGATomics' superior performance in cancer diagnosis. Moreover, HeteroGATomics enhances interpretability by identifying important biomarkers contributing to the diagnosis outcomes.
Authors: Cho-Chun Chiu, Tuan Nguyen, Ting He, Shiqiang Wang, Beom-Su Kim, Ki-Il Kim
Abstract: We consider a novel active learning problem motivated by the need of learning machine learning models for health monitoring in wireless body area network (WBAN). Due to the limited resources at body sensors, collecting each unlabeled sample in WBAN incurs a nontrivial cost. Moreover, training health monitoring models typically requires labels indicating the patient's health state that need to be generated by healthcare professionals, which cannot be obtained at the same pace as data collection. These challenges make our problem fundamentally different from classical active learning, where unlabeled samples are free and labels can be queried in real time. To handle these challenges, we propose a two-phased active learning method, consisting of an online phase where a coreset construction algorithm is proposed to select a subset of unlabeled samples based on their noisy predictions, and an offline phase where the selected samples are labeled to train the target model. The samples selected by our algorithm are proved to yield a guaranteed error in approximating the full dataset in evaluating the loss function. Our evaluation based on real health monitoring data and our own experimentation demonstrates that our solution can drastically save the data curation cost without sacrificing the quality of the target model.
Authors: Borong Zhang, Mart\'in Guerra, Qin Li, Leonardo Zepeda-N\'u\~nez
Abstract: We present \textit{Wideband back-projection diffusion}, an end-to-end probabilistic framework for approximating the posterior distribution induced by the inverse scattering map from wideband scattering data. This framework leverages conditional diffusion models coupled with the underlying physics of wave-propagation and symmetries in the problem, to produce highly accurate reconstructions. The framework introduces a factorization of the score function into a physics-based latent representation inspired by the filtered back-propagation formula and a conditional score function conditioned on this latent representation. These two steps are also constrained to obey symmetries in the formulation while being amenable to compression by imposing the rank structure found in the filtered back-projection formula. As a result, empirically, our framework is able to provide sharp reconstructions effortlessly, even recovering sub-Nyquist features in the multiple-scattering regime. It has low-sample and computational complexity, its number of parameters scales sub-linearly with the target resolution, and it has stable training dynamics.
Authors: Mitchelle Rasquinha, Gil Tabak
Abstract: As deep learning methodologies have developed, it has been generally agreed that increasing neural network size improves model quality. However, this is at the expense of memory and compute requirements, which also need to be increased. Various efficiency techniques have been proposed to rein in hardware costs, one being the use of low precision numerics. Recent accelerators have introduced several different 8-bit data types to help accommodate DNNs in terms of numerics. In this paper, we identify a metric driven methodology to aid in the choice of numerics. We demonstrate how such a methodology can help scale training of a language representation model. The technique can be generalized to other model architectures.
Authors: Yuxin Wang, Duanyu Feng, Yongfu Dai, Zhengyu Chen, Jimin Huang, Sophia Ananiadou, Qianqian Xie, Hao Wang
Abstract: Data serves as the fundamental foundation for advancing deep learning, particularly tabular data presented in a structured format, which is highly conducive to modeling. However, even in the era of LLM, obtaining tabular data from sensitive domains remains a challenge due to privacy or copyright concerns. Hence, exploring how to effectively use models like LLMs to generate realistic and privacy-preserving synthetic tabular data is urgent. In this paper, we take a step forward to explore LLMs for tabular data synthesis and privacy protection, by introducing a new framework HARMONIC for tabular data generation and evaluation. In the tabular data generation of our framework, unlike previous small-scale LLM-based methods that rely on continued pre-training, we explore the larger-scale LLMs with fine-tuning to generate tabular data and enhance privacy. Based on idea of the k-nearest neighbors algorithm, an instruction fine-tuning dataset is constructed to inspire LLMs to discover inter-row relationships. Then, with fine-tuning, LLMs are trained to remember the format and connections of the data rather than the data itself, which reduces the risk of privacy leakage. In the evaluation part of our framework, we develop specific privacy risk metrics DLT for LLM synthetic data generation, as well as performance evaluation metrics LLE for downstream LLM tasks. Our experiments find that this tabular data generation framework achieves equivalent performance to existing methods with better privacy, which also demonstrates our evaluation framework for the effectiveness of synthetic data and privacy risks in LLM scenarios.
Authors: Saurabh Kumar, Hong Jun Jeon, Alex Lewandowski, Benjamin Van Roy
Abstract: The "small agent, big world" frame offers a conceptual view that motivates the need for continual learning. The idea is that a small agent operating in a much bigger world cannot store all information that the world has to offer. To perform well, the agent must be carefully designed to ingest, retain, and eject the right information. To enable the development of performant continual learning agents, a number of synthetic environments have been proposed. However, these benchmarks suffer from limitations, including unnatural distribution shifts and a lack of fidelity to the "small agent, big world" framing. This paper aims to formalize two desiderata for the design of future simulated environments. These two criteria aim to reflect the objectives and complexity of continual learning in practical settings while enabling rapid prototyping of algorithms on a smaller scale.
Authors: Jinghui Yuan, Chusheng Zeng, Fangyuan Xie, Zhe Cao, Rong Wang, Feiping Nie, Xuelong Li
Abstract: Clustering is a fundamental task in machine learning and data science, and similarity graph-based clustering is an important approach within this domain. Doubly stochastic symmetric similarity graphs provide numerous benefits for clustering problems and downstream tasks, yet learning such graphs remains a significant challenge. Marcus theorem states that a strictly positive symmetric matrix can be transformed into a doubly stochastic symmetric matrix by diagonal matrices. However, in clustering, learning sparse matrices is crucial for computational efficiency. We extend Marcus theorem by proposing the Marcus mapping, which indicates that certain sparse matrices can also be transformed into doubly stochastic symmetric matrices via diagonal matrices. Additionally, we introduce rank constraints into the clustering problem and propose the Doubly Stochastic Adaptive Neighbors Clustering algorithm based on the Marcus Mapping (ANCMM). This ensures that the learned graph naturally divides into the desired number of clusters. We validate the effectiveness of our algorithm through extensive comparisons with state-of-the-art algorithms. Finally, we explore the relationship between the Marcus mapping and optimal transport. We prove that the Marcus mapping solves a specific type of optimal transport problem and demonstrate that solving this problem through Marcus mapping is more efficient than directly applying optimal transport methods.
Authors: Jinghui Yuan, Weijin Jiang, Zhe Cao, Fangyuan Xie, Rong Wang, Feiping Nie, Xuelong Li
Abstract: Ensemble learning is a method that leverages weak learners to produce a strong learner. However, obtaining a large number of base learners requires substantial time and computational resources. Therefore, it is meaningful to study how to achieve the performance typically obtained with many base learners using only a few. We argue that to achieve this, it is essential to enhance both classification performance and generalization ability during the ensemble process. To increase model accuracy, each weak base learner needs to be more efficiently integrated. It is observed that different base learners exhibit varying levels of accuracy in predicting different classes. To capitalize on this, we introduce confidence tensors $\tilde{\mathbf{\Theta}}$ and $\tilde{\mathbf{\Theta}}_{rst}$ signifies that the $t$-th base classifier assigns the sample to class $r$ while it actually belongs to class $s$. To the best of our knowledge, this is the first time an evaluation of the performance of base classifiers across different classes has been proposed. The proposed confidence tensor compensates for the strengths and weaknesses of each base classifier in different classes, enabling the method to achieve superior results with a smaller number of base learners. To enhance generalization performance, we design a smooth and convex objective function that leverages the concept of margin, making the strong learner more discriminative. Furthermore, it is proved that in gradient matrix of the loss function, the sum of each column's elements is zero, allowing us to solve a constrained optimization problem using gradient-based methods. We then compare our algorithm with random forests of ten times the size and other classical methods across numerous datasets, demonstrating the superiority of our approach.
Authors: Ali Kashefi
Abstract: We present Kolmogorov-Arnold PointNet (KA-PointNet) as a novel supervised deep learning framework for the prediction of incompressible steady-state fluid flow fields in irregular domains, where the predicted fields are a function of the geometry of the domains. In KA-PointNet, we implement shared Kolmogorov-Arnold Networks (KANs) in the segmentation branch of the PointNet architecture. We utilize Jacobi polynomials to construct shared KANs. As a benchmark test case, we consider incompressible laminar steady-state flow over a cylinder, where the geometry of its cross-section varies over the data set. We investigate the performance of Jacobi polynomials with different degrees as well as special cases of Jacobi polynomials such as Legendre polynomials, Chebyshev polynomials of the first and second kinds, and Gegenbauer polynomials, in terms of the computational cost of training and accuracy of prediction of the test set. Additionally, we compare the performance of PointNet with shared KANs (i.e., KA-PointNet) and PointNet with shared Multilayer Perceptrons (MLPs). It is observed that when the number of trainable parameters is approximately equal, PointNet with shared KANs (i.e., KA-PointNet) outperforms PointNet with shared MLPs.
Authors: Xinghao Dong, Chuanqi Chen, Jin-Long Wu
Abstract: Closure models are widely used in simulating complex multiscale dynamical systems such as turbulence and the earth system, for which direct numerical simulation that resolves all scales is often too expensive. For those systems without a clear scale separation, deterministic and local closure models often lack enough generalization capability, which limits their performance in many real-world applications. In this work, we propose a data-driven modeling framework for constructing stochastic and non-local closure models via conditional diffusion model and neural operator. Specifically, the Fourier neural operator is incorporated into a score-based diffusion model, which serves as a data-driven stochastic closure model for complex dynamical systems governed by partial differential equations (PDEs). We also demonstrate how accelerated sampling methods can improve the efficiency of the data-driven stochastic closure model. The results show that the proposed methodology provides a systematic approach via generative machine learning techniques to construct data-driven stochastic closure models for multiscale dynamical systems with continuous spatiotemporal fields.
Authors: Joonhyuk Seo, Chanik Kang, Dongjin Seo, Haejun Chung
Abstract: Designing photonic structures requires electromagnetic simulations, which often require high computational costs. Researchers have developed surrogate solvers for predicting electric fields to alleviate the computational issues. However, existing surrogate solvers are limited to performing inference at fixed simulation conditions and require retraining for different conditions. To address this, we propose Wave Interpolation Neural Operator (WINO), a novel surrogate solver enabling simulation condition interpolation across a continuous spectrum of broadband wavelengths. WINO introduces the Fourier Group Convolution Shuffling operator and a new conditioning method to efficiently predict electric fields from both trained and untrained wavelength data, achieving significant improvements in parameter efficiency and spectral interpolation performance. Our model demonstrates approximately 100 times faster performance than traditional finite-difference frequency-domain simulations. Moreover, compared to the state-of-the-art model, we achieve a 74% reduction in parameters and 80.5% improvements in prediction accuracy for untrained wavelengths, and 13.2% improvements for trained wavelengths.
Authors: Pengcheng Gao, Zicheng Gao, Ye Yuan
Abstract: High quality spatiotemporal signal is vitally important for real application scenarios like energy management, traffic planning and cyber security. Due to the uncontrollable factors like abrupt sensors breakdown or communication fault, the spatiotemporal signal collected by sensors is always incomplete. A dynamic graph convolutional network (DGCN) is effective for processing spatiotemporal signal recovery. However, it adopts a static GCN and a sequence neural network to explore the spatial and temporal patterns, separately. Such a separated two-step processing is loose spatiotemporal, thereby failing to capture the complex inner spatiotemporal correlation. To address this issue, this paper proposes a Compact-Dynamic Graph Convolutional Network (CDGCN) for spatiotemporal signal recovery with the following two-fold ideas: a) leveraging the tensor M-product to build a unified tensor graph convolution framework, which considers both spatial and temporal patterns simultaneously; and b) constructing a differential smoothness-based objective function to reduce the noise interference in spatiotemporal signal, thereby further improve the recovery accuracy. Experiments on real-world spatiotemporal datasets demonstrate that the proposed CDGCN significantly outperforms the state-of-the-art models in terms of recovery accuracy.
Authors: Anwesha Mukherjee, Rajkumar Buyya
Abstract: Federated learning has become an emerging technology for data analysis for IoT applications. This paper implements centralized and decentralized federated learning frameworks for crop yield prediction based on Long Short-Term Memory Network. For centralized federated learning, multiple clients and one server is considered, where the clients exchange their model updates with the server that works as the aggregator to build the global model. For the decentralized framework, a collaborative network is formed among the devices either using ring topology or using mesh topology. In this network, each device receives model updates from the neighbour devices, and performs aggregation to build the upgraded model. The performance of the centralized and decentralized federated learning frameworks are evaluated in terms of prediction accuracy, precision, recall, F1-Score, and training time. The experimental results present that $\geq$97% and $>$97.5% prediction accuracy are achieved using the centralized and decentralized federated learning-based frameworks respectively. The results also show that the using centralized federated learning the response time can be reduced by $\sim$75% than the cloud-only framework. Finally, the future research directions of the use of federated learning in crop yield prediction are explored in this paper.
Authors: Haozhe Ma, Zhengding Luo, Thanh Vinh Vo, Kuankuan Sima, Tze-Yun Leong
Abstract: Reward shaping addresses the challenge of sparse rewards in reinforcement learning by constructing denser and more informative reward signals. To achieve self-adaptive and highly efficient reward shaping, we propose a novel method that incorporates success rates derived from historical experiences into shaped rewards. Our approach utilizes success rates sampled from Beta distributions, which dynamically evolve from uncertain to reliable values as more data is collected. Initially, the self-adaptive success rates exhibit more randomness to encourage exploration. Over time, they become more certain to enhance exploitation, thus achieving a better balance between exploration and exploitation. We employ Kernel Density Estimation (KDE) combined with Random Fourier Features (RFF) to derive the Beta distributions, resulting in a computationally efficient implementation in high-dimensional continuous state spaces. This method provides a non-parametric and learning-free approach. The proposed method is evaluated on a wide range of continuous control tasks with sparse and delayed rewards, demonstrating significant improvements in sample efficiency and convergence stability compared to several baselines.
Authors: Zixiang Wang, Hao Yan, Changsong Wei, Junyu Wang, Shi Bo, Minheng Xiao
Abstract: The behavior decision-making subsystem is a key component of the autonomous driving system, which reflects the decision-making ability of the vehicle and the driver, and is an important symbol of the high-level intelligence of the vehicle. However, the existing rule-based decision-making schemes are limited by the prior knowledge of designers, and it is difficult to cope with complex and changeable traffic scenarios. In this work, an advanced deep reinforcement learning model is adopted, which can autonomously learn and optimize driving strategies in a complex and changeable traffic environment by modeling the driving decision-making process as a reinforcement learning problem. Specifically, we used Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) for comparative experiments. DQN guides the agent to choose the best action by approximating the state-action value function, while PPO improves the decision-making quality by optimizing the policy function. We also introduce improvements in the design of the reward function to promote the robustness and adaptability of the model in real-world driving situations. Experimental results show that the decision-making strategy based on deep reinforcement learning has better performance than the traditional rule-based method in a variety of driving tasks.
Authors: Yannik Schnitzer, Alessandro Abate, David Parker
Abstract: We present a data-driven approach for learning MDP policies that are robust across stochastic environments whose transition probabilities are defined by parameters with an unknown distribution. We produce probably approximately correct (PAC) guarantees for the performance of these learned policies in a new, unseen environment over the unknown distribution. Our approach is based on finite samples of the MDP environments, for each of which we build an approximation of the model as an interval MDP, by exploring a set of generated trajectories. We use the built approximations to synthesise a single policy that performs well (meets given requirements) across the sampled environments, and furthermore bound its risk (of not meeting the given requirements) when deployed in an unseen environment. Our procedure offers a trade-off between the guaranteed performance of the learned policy and the risk of not meeting the guarantee in an unseen environment. Our approach exploits knowledge of the environment's state space and graph structure, and we show how additional knowledge of its parametric structure can be leveraged to optimize learning and to obtain tighter guarantees from less samples. We evaluate our approach on a diverse range of established benchmarks, demonstrating that we can generate highly performing and robust policies, along with guarantees that tightly quantify their performance and the associated risk.
Authors: D. Dhinakaran, S. Edwin Raja, M. Thiyagarajan, J. Jeno Jasmine, P. Raghavan
Abstract: The rapid integration of machine learning methodologies in healthcare has ignited innovative strategies for disease prediction, particularly with the vast repositories of Electronic Health Records (EHR) data. This article delves into the realm of multi-disease prediction, presenting a comprehensive study that introduces a pioneering ensemble feature selection model. This model, designed to optimize learning systems, combines statistical, deep, and optimally selected features through the innovative Stabilized Energy Valley Optimization with Enhanced Bounds (SEV-EB) algorithm. The objective is to achieve unparalleled accuracy and stability in predicting various disorders. This work proposes an advanced ensemble model that synergistically integrates statistical, deep, and optimally selected features. This combination aims to enhance the predictive power of the model by capturing diverse aspects of the health data. At the heart of the proposed model lies the SEV-EB algorithm, a novel approach to optimal feature selection. The algorithm introduces enhanced bounds and stabilization techniques, contributing to the robustness and accuracy of the overall prediction model. To further elevate the predictive capabilities, an HSC-AttentionNet is introduced. This network architecture combines deep temporal convolution capabilities with LSTM, allowing the model to capture both short-term patterns and long-term dependencies in health data. Rigorous evaluations showcase the remarkable performance of the proposed model. Achieving a 95% accuracy and 94% F1-score in predicting various disorders, the model surpasses traditional methods, signifying a significant advancement in disease prediction accuracy. The implications of this research extend beyond the confines of academia.
Authors: Furong Peng, Kang Liu, Xuan Lu, Yuhua Qian, Hongren Yan, Chao Ma
Abstract: Graph Convolutional Neural Network (GCN), a widely adopted method for analyzing relational data, enhances node discriminability through the aggregation of neighboring information. Usually, stacking multiple layers can improve the performance of GCN by leveraging information from high-order neighbors. However, the increase of the network depth will induce the over-smoothing problem, which can be attributed to the quality and quantity of neighbors changing: (a) neighbor quality, node's neighbors become overlapping in high order, leading to aggregated information becoming indistinguishable, (b) neighbor quantity, the exponentially growing aggregated neighbors submerges the node's initial feature by recursively aggregating operations. Current solutions mainly focus on one of the above causes and seldom consider both at once. Aiming at tackling both causes of over-smoothing in one shot, we introduce a simple Two-Sided Constraint (TSC) for GCNs, comprising two straightforward yet potent techniques: random masking and contrastive constraint. The random masking acts on the representation matrix's columns to regulate the degree of information aggregation from neighbors, thus preventing the convergence of node representations. Meanwhile, the contrastive constraint, applied to the representation matrix's rows, enhances the discriminability of the nodes. Designed as a plug-in module, TSC can be easily coupled with GCN or SGC architectures. Experimental analyses on diverse real-world graph datasets verify that our approach markedly reduces the convergence of node's representation and the performance degradation in deeper GCN.
Authors: Jiapeng Zhu, Zichen Ding, Jianxiang Yu, Jiaqi Tan, Xiang Li, Weining Qian
Abstract: The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt tuning approaches tailored specialized prompting functions for Graph Neural Network (GNN) models pre-trained with specific strategies, such as edge prediction, thus limiting their applicability. In contrast, another pioneering line of research has explored universal prompting via adding prompts to the input graph's feature space, thereby removing the reliance on specific pre-training strategies. However, the necessity to add feature prompts to all nodes remains an open question. Motivated by findings from prompt tuning research in the NLP domain, which suggest that highly capable pre-trained models need less conditioning signal to achieve desired behaviors, we advocate for strategically incorporating necessary and lightweight feature prompts to certain graph nodes to enhance downstream task performance. This introduces a combinatorial optimization problem, requiring a policy to decide 1) which nodes to prompt and 2) what specific feature prompts to attach. We then address the problem by framing the prompt incorporation process as a sequential decision-making problem and propose our method, RELIEF, which employs Reinforcement Learning (RL) to optimize it. At each step, the RL agent selects a node (discrete action) and determines the prompt content (continuous action), aiming to maximize cumulative performance gain. Extensive experiments on graph and node-level tasks with various pre-training strategies in few-shot scenarios demonstrate that our RELIEF outperforms fine-tuning and other prompt-based approaches in classification performance and data efficiency.
Authors: Shiwei Li, Wenchao Xu, Haozhao Wang, Xing Tang, Yining Qi, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li
Abstract: Federated learning is a promising distributed machine learning paradigm that can effectively exploit large-scale data without exposing users' privacy. However, it may incur significant communication overhead, thereby potentially impairing the training efficiency. To address this challenge, numerous studies suggest binarizing the model updates. Nonetheless, traditional methods usually binarize model updates in a post-training manner, resulting in significant approximation errors and consequent degradation in model accuracy. To this end, we propose Federated Binarization-Aware Training (FedBAT), a novel framework that directly learns binary model updates during the local training process, thus inherently reducing the approximation errors. FedBAT incorporates an innovative binarization operator, along with meticulously designed derivatives to facilitate efficient learning. In addition, we establish theoretical guarantees regarding the convergence of FedBAT. Extensive experiments are conducted on four popular datasets. The results show that FedBAT significantly accelerates the convergence and exceeds the accuracy of baselines by up to 9\%, even surpassing that of FedAvg in some cases.
Authors: Anna Vettoruzzo, Joaquin Vanschoren, Mohamed-Rafik Bouguelia, Thorsteinn R\"ognvaldsson
Abstract: Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods are highly prone to overwrite previously learned patterns and thus forget past experience. Instead, model parameters should be updated selectively and carefully, avoiding unnecessary forgetting while optimally leveraging previously learned patterns to accelerate future learning. Since hand-crafting effective update mechanisms is difficult, we propose meta-learning a transformer-based optimizer to enhance CL. This meta-learned optimizer uses attention to learn the complex relationships between model parameters across a stream of tasks, and is designed to generate effective weight updates for the current task while preventing catastrophic forgetting on previously encountered tasks. Evaluations on benchmark datasets like SplitMNIST, RotatedMNIST, and SplitCIFAR-100 affirm the efficacy of the proposed approach in terms of both forward and backward transfer, even on small sets of labeled data, highlighting the advantages of integrating a meta-learned optimizer within the continual learning framework.
Authors: Shiwei Li, Yingyi Cheng, Haozhao Wang, Xing Tang, Shijie Xu, Weihong Luo, Yuhua Li, Dugang Liu, Xiuqiang He, and Ruixuan Li
Abstract: Federated learning is a promising distributed training paradigm that effectively safeguards data privacy. However, it may involve significant communication costs, which hinders training efficiency. In this paper, we aim to enhance communication efficiency from a new perspective. Specifically, we request the distributed clients to find optimal model updates relative to global model parameters within predefined random noise. For this purpose, we propose Federated Masked Random Noise (FedMRN), a novel framework that enables clients to learn a 1-bit mask for each model parameter and apply masked random noise (i.e., the Hadamard product of random noise and masks) to represent model updates. To make FedMRN feasible, we propose an advanced mask training strategy, called progressive stochastic masking (PSM). After local training, each client only need to transmit local masks and a random seed to the server. Additionally, we provide theoretical guarantees for the convergence of FedMRN under both strongly convex and non-convex assumptions. Extensive experiments are conducted on four popular datasets. The results show that FedMRN exhibits superior convergence speed and test accuracy compared to relevant baselines, while attaining a similar level of accuracy as FedAvg.
Authors: Christodoulos Kechris, Jonathan Dan, Jose Miranda, David Atienza
Abstract: Deep learning time-series processing often relies on convolutional neural networks with overlapping windows. This overlap allows the network to produce an output faster than the window length. However, it introduces additional computations. This work explores the potential to optimize computational efficiency during inference by exploiting convolution's shift-invariance properties to skip the calculation of layer activations between successive overlapping windows. Although convolutions are shift-invariant, zero-padding and pooling operations, widely used in such networks, are not efficient and complicate efficient streaming inference. We introduce StreamiNNC, a strategy to deploy Convolutional Neural Networks for online streaming inference. We explore the adverse effects of zero padding and pooling on the accuracy of streaming inference, deriving theoretical error upper bounds for pooling during streaming. We address these limitations by proposing signal padding and pooling alignment and provide guidelines for designing and deploying models for StreamiNNC. We validate our method in simulated data and on three real-world biomedical signal processing applications. StreamiNNC achieves a low deviation between streaming output and normal inference for all three networks (2.03 - 3.55% NRMSE). This work demonstrates that it is possible to linearly speed up the inference of streaming CNNs processing overlapping windows, negating the additional computation typically incurred by overlapping windows.
Authors: W. S. Leite, R. C. de Lamare
Abstract: This paper investigates the problem of direction-of-arrival (DOA) estimation using multiple partially-calibrated sparse subarrays. In particular, we present the Generalized Coarray Multiple Signal Classification (GCA-MUSIC) DOA estimation algorithm to scenarios with partially-calibrated sparse subarrays. The proposed GCA-MUSIC algorithm exploits the difference coarray for each subarray, followed by a specific pseudo-spectrum merging rule that is based on the intersection of the signal subspaces associated to each subarray. This rule assumes that there is no a priori knowledge about the cross-covariance between subarrays. In that way, only the second-order statistics of each subarray are used to estimate the directions with increased degrees of freedom, i.e., the estimation procedure preserves the coarray Multiple Signal Classification and sparse arrays properties to estimate more sources than the number of physical sensors in each subarray. Numerical simulations show that the proposed GCA-MUSIC has better performance than other similar strategies.
Authors: Simon Mandlik, Tomas Pevny, Vaclav Smidl, Lukas Bajer
Abstract: Detection of malicious behavior in a large network is a challenging problem for machine learning in computer security, since it requires a model with high expressive power and scalable inference. Existing solutions struggle to achieve this feat -- current cybersec-tailored approaches are still limited in expressivity, and methods successful in other domains do not scale well for large volumes of data, rendering frequent retraining impossible. This work proposes a new perspective for learning from graph data that is modeling network entity interactions as a large heterogeneous graph. High expressivity of the method is achieved with neural network architecture HMILnet that naturally models this type of data and provides theoretical guarantees. The scalability is achieved by pursuing local graph inference, i.e., classifying individual vertices and their neighborhood as independent samples. Our experiments exhibit improvement over the state-of-the-art Probabilistic Threat Propagation (PTP) algorithm, show a further threefold accuracy improvement when additional data is used, which is not possible with the PTP algorithm, and demonstrate the generalization capabilities of the method to new, previously unseen entities.
Authors: Jihao Gu, Shuai Chen, Zelin Wang, Yibo Zhang, Ping Gong
Abstract: With the increasing number of parameters in large pre-trained models, LoRA as a parameter-efficient fine-tuning(PEFT) method is widely used for not adding inference overhead. The LoRA method assumes that weight changes during fine-tuning can be approximated by low-rank matrices. However, the rank values need to be manually verified to match different downstream tasks, and they cannot accommodate the varying importance of different layers in the model. In this work, we first analyze the relationship between the performance of different layers and their ranks using SVD. Based on this, we design the Singular-Value Based Adaptive Low-Rank Adaption(SARA), which adaptively finds the rank during initialization by performing SVD on the pre-trained weights. Additionally, we explore the Mixture-of-SARA(Mo-SARA), which significantly reduces the number of parameters by fine-tuning only multiple parallel sets of singular values controlled by a router. Extensive experiments on various complex tasks demonstrate the simplicity and parameter efficiency of our methods. They can effectively and adaptively find the most suitable rank for each layer of each model.
Authors: Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar
Abstract: Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model's distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a "compute-optimal" scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.
Authors: Victor Kasatkin, Evgeny Mozgunov, Nicholas Ezzell, Utkarsh Mishra, Itay Hen, Daniel Lidar
Abstract: Estimation of the Fisher Information Metric (FIM-estimation) is an important task that arises in unsupervised learning of phase transitions, a problem proposed by physicists. This work completes the definition of the task by defining rigorous evaluation metrics distMSE, distMSEPS, and distRE and introduces ClassiFIM, a novel machine learning method designed to solve the FIM-estimation task. Unlike existing methods for unsupervised learning of phase transitions, ClassiFIM directly estimates a well-defined quantity (the FIM), allowing it to be rigorously compared to any present and future other methods that estimate the same. ClassiFIM transforms a dataset for the FIM-estimation task into a dataset for an auxiliary binary classification task and involves selecting and training a model for the latter. We prove that the output of ClassiFIM approaches the exact FIM in the limit of infinite dataset size and under certain regularity conditions. We implement ClassiFIM on multiple datasets, including datasets describing classical and quantum phase transitions, and find that it achieves a good ground truth approximation with modest computational resources. Furthermore, we independently implement two alternative state-of-the-art methods for unsupervised estimation of phase transition locations on the same datasets and find that ClassiFIM predicts such locations at least as well as these other methods. To emphasize the generality of our method, we also propose and generate the MNIST-CNN dataset, which consists of the output of CNNs trained on MNIST for different hyperparameter choices. Using ClassiFIM on this dataset suggests there is a phase transition in the distribution of image-prediction pairs for CNNs trained on MNIST, demonstrating the broad scope of FIM-estimation beyond physics.
Authors: Borong Zhang, Leonardo Zepeda-N\'u\~nez, Qin Li
Abstract: This paper introduces a novel deep neural network architecture for solving the inverse scattering problem in frequency domain with wide-band data, by directly approximating the inverse map, thus avoiding the expensive optimization loop of classical methods. The architecture is motivated by the filtered back-projection formula in the full aperture regime and with homogeneous background, and it leverages the underlying equivariance of the problem and compressibility of the integral operator. This drastically reduces the number of training parameters, and therefore the computational and sample complexity of the method. In particular, we obtain an architecture whose number of parameters scale sub-linearly with respect to the dimension of the inputs, while its inference complexity scales super-linearly but with very small constants. We provide several numerical tests that show that the current approach results in better reconstruction than optimization-based techniques such as full-waveform inversion, but at a fraction of the cost while being competitive with state-of-the-art machine learning methods.
Authors: Chenghan Li, Or Sharir, Shunyue Yuan, Garnet K. Chan
Abstract: Drawing inspiration from the domain of image super-resolution, we view the electron density as a 3D grayscale image and use a convolutional residual network to transform a crude and trivially generated guess of the molecular density into an accurate ground-state quantum mechanical density. We find that this model outperforms all prior density prediction approaches. Because the input is itself a real-space density, the predictions are equivariant to molecular symmetry transformations even though the model is not constructed to be. Due to its simplicity, the model is directly applicable to unseen molecular conformations and chemical elements. We show that fine-tuning on limited new data provides high accuracy even in challenging cases of exotic elements and charge states. Our work suggests new routes to learning real-space physical quantities drawing from the established ideas of image processing.
Authors: Dionis Barcari, David Gamez, Aliya Grig
Abstract: Foundation models have had a big impact in recent years and billions of dollars are being invested in them in the current AI boom. The more popular ones, such as Chat-GPT, are trained on large amounts of Internet data. However, it is becoming apparent that this data is likely to be exhausted soon, and technology companies are looking for new sources of data to train the next generation of foundation models. Reinforcement learning, RAG, prompt engineering and cognitive modelling are often used to fine-tune and augment the behaviour of foundation models. These techniques have been used to replicate people, such as Caryn Marjorie. These chatbots are not based on people's actual emotional and physiological responses to their environment, so they are, at best, a surface-level approximation to the characters they are imitating. To address these issues, we have developed a recording rig that captures what the wearer is seeing and hearing as well as their skin conductance (GSR), facial expression and brain state (14 channel EEG). AI algorithms are used to process this data into a rich picture of the environment and internal states of the subject. Foundation models trained on this data could replicate human behaviour much more accurately than the personality models that have been developed so far. This type of model has many potential applications, including recommendation, personal assistance, GAN systems, dating and recruitment. This paper gives some background to this work and describes the recording rig and preliminary tests of its functionality. It then suggests how a new type of foundation model could be created from the data captured by the rig and outlines some applications. Data gathering and model training are expensive, so we are currently working on the launch of a start-up that could raise funds for the next stage of the project.
Authors: Pushkar Jajoria, James McDermott
Abstract: This study introduces a text-conditioned approach to generating drumbeats with Latent Diffusion Models (LDMs). It uses informative conditioning text extracted from training data filenames. By pretraining a text and drumbeat encoder through contrastive learning within a multimodal network, aligned following CLIP, we align the modalities of text and music closely. Additionally, we examine an alternative text encoder based on multihot text encodings. Inspired by musics multi-resolution nature, we propose a novel LSTM variant, MultiResolutionLSTM, designed to operate at various resolutions independently. In common with recent LDMs in the image space, it speeds up the generation process by running diffusion in a latent space provided by a pretrained unconditional autoencoder. We demonstrate the originality and variety of the generated drumbeats by measuring distance (both over binary pianorolls and in the latent space) versus the training dataset and among the generated drumbeats. We also assess the generated drumbeats through a listening test focused on questions of quality, aptness for the prompt text, and novelty. We show that the generated drumbeats are novel and apt to the prompt text, and comparable in quality to those created by human musicians.
Authors: Johannes Erdmann, Florian Mausolf, Jan Lukas Sp\"ah
Abstract: Recently, Kolmogorov-Arnold Networks (KANs) have been proposed as an alternative to multilayer perceptrons, suggesting advantages in performance and interpretability. We study a typical binary event classification task in high-energy physics including high-level features and comment on the performance and interpretability of KANs in this context. We find that the learned activation functions of a one-layer KAN resemble the log-likelihood ratio of the input features. In deeper KANs, the activations in the first KAN layer differ from those in the one-layer KAN, which indicates that the deeper KANs learn more complex representations of the data. We study KANs with different depths and widths and we compare them to multilayer perceptrons in terms of performance and number of trainable parameters. For the chosen classification task, we do not find that KANs are more parameter efficient. However, small KANs may offer advantages in terms of interpretability that come at the cost of only a moderate loss in performance.
Authors: McKell Woodland, Nihil Patel, Austin Castelo, Mais Al Taie, Mohamed Eltaher, Joshua P. Yung, Tucker J. Netherton, Tiffany L. Calderone, Jessica I. Sanchez, Darrel W. Cleere, Ahmed Elsaiey, Nakul Gupta, David Victor, Laura Beretta, Ankit B. Patel Kristy K. Brock
Abstract: Clinically deployed deep learning-based segmentation models are known to fail on data outside of their training distributions. While clinicians review the segmentations, these models tend to perform well in most instances, which could exacerbate automation bias. Therefore, detecting out-of-distribution images at inference is critical to warn the clinicians that the model likely failed. This work applied the Mahalanobis distance (MD) post hoc to the bottleneck features of four Swin UNETR and nnU-net models that segmented the liver on T1-weighted magnetic resonance imaging and computed tomography. By reducing the dimensions of the bottleneck features with either principal component analysis or uniform manifold approximation and projection, images the models failed on were detected with high performance and minimal computational load. In addition, this work explored a non-parametric alternative to the MD, a k-th nearest neighbors distance (KNN). KNN drastically improved scalability and performance over MD when both were applied to raw and average-pooled bottleneck features.
Authors: Monika Kwiatkowski, Simon Matern, Olaf Hellwich
Abstract: In this work, we introduce a deep-learning framework designed for estimating dense image correspondences. Our fully convolutional model generates dense feature maps for images, where each pixel is associated with a descriptor that can be matched across multiple images. Unlike previous methods, our model is trained on synthetic data that includes significant distortions, such as perspective changes, illumination variations, shadows, and specular highlights. Utilizing contrastive learning, our feature maps achieve greater invariance to these distortions, enabling robust matching. Notably, our method eliminates the need for a keypoint detector, setting it apart from many existing image-matching techniques.
Authors: Adil Soubki, Shyne Choi, Owen Rambow
Abstract: We propose a framework for analyzing discourse by combining two interdependent concepts from sociolinguistic theory: face acts and politeness. While politeness has robust existing tools and data, face acts are less resourced. We introduce a new corpus created by annotating Wikipedia talk pages with face acts and we use this to train a face act tagger. We then employ our framework to study how face and politeness interact with gender and power in discussions between Wikipedia editors. Among other findings, we observe that female Wikipedians are not only more polite, which is consistent with prior studies, but that this difference corresponds with significantly more language directed at humbling aspects of their own face. Interestingly, the distinction nearly vanishes once limiting to editors with administrative power.
Authors: Eric Bax, Arundhyoti Sarkar, Alex Shtoff
Abstract: Requiring statistical significance at multiple interim analyses to declare a statistically significant result for an AB test allows less stringent requirements for significance at each interim analysis. Repeated repeated significance competes well with methods built on assumptions about the test -- assumptions that may be impossible to evaluate a priori and may require extra data to evaluate empirically. Instead, requiring repeated significance allows the data itself to prove directly that the required results are not due to chance alone. We explain how to apply tests with repeated significance to continuously monitor unbounded tests -- tests that do not have an a priori bound on running time or number of observations. We show that it is impossible to maintain a constant requirement for significance for unbounded tests, but that we can come arbitrarily close to that goal.
Authors: Harrison H. Li, Chaoyu Yu
Abstract: In designing an online A/B experiment, it is crucial to select a sample size and duration that ensure the resulting confidence interval (CI) for the treatment effect is the right width to detect an effect of meaningful magnitude with sufficient statistical power without wasting resources. While the relationship between sample size and CI width is well understood, the effect of experiment duration on CI width remains less clear. This paper provides an analytical formula for the width of a CI based on a ratio treatment effect estimator as a function of both sample size (N) and duration (T). The formula is derived from a mixed effects model with two variance components. One component, referred to as the temporal variance, persists over time for experiments where the same users are kept in the same experiment arm across different days. The remaining error variance component, by contrast, decays to zero as T gets large. The formula we derive introduces a key parameter that we call the user-specific temporal correlation (UTC), which quantifies the relative sizes of the two variance components and can be estimated from historical experiments. Higher UTC indicates a slower decay in CI width over time. On the other hand, when the UTC is 0 -- as for experiments where users shuffle in and out of the experiment across days -- the CI width decays at the standard parametric 1/T rate. We also study how access to pre-period data for the users in the experiment affects the CI width decay. We show our formula closely explains CI widths on real A/B experiments at YouTube.
Authors: Costantino Carugno, Maurizio Ferrari Dacrema, Paolo Cremonesi
Abstract: The recent availability of quantum annealers as cloud-based services has enabled new ways to handle machine learning problems, and several relevant algorithms have been adapted to run on these devices. In a recent work, linear regression was formulated as a quadratic binary optimization problem that can be solved via quantum annealing. Although this approach promises a computational time advantage for large datasets, the quality of the solution is limited by the necessary use of a precision vector, used to approximate the real-numbered regression coefficients in the quantum formulation. In this work, we focus on the practical challenge of improving the precision vector encoding: instead of setting an array of generic values equal for all coefficients, we allow each one to be expressed by its specific precision, which is tuned with a simple adaptive algorithm. This approach is evaluated on synthetic datasets of increasing size, and linear regression is solved using the D-Wave Advantage quantum annealer, as well as classical solvers. To the best of our knowledge, this is the largest dataset ever evaluated for linear regression on a quantum annealer. The results show that our formulation is able to deliver improved solution quality in all instances, and could better exploit the potential of current quantum devices.
Authors: William Patton, Jeff L. Rhoades, Marwan Zouinkhi, David G. Ackerman, Caroline Malin-Mayor, Diane Adjavon, Larissa Heinrich, Davis Bennett, Yurii Zubov, CellMap Project Team, Aubrey V. Weigel, Jan Funke
Abstract: DaCapo is a specialized deep learning library tailored to expedite the training and application of existing machine learning approaches on large, near-isotropic image data. In this correspondence, we introduce DaCapo's unique features optimized for this specific domain, highlighting its modular structure, efficient experiment management tools, and scalable deployment capabilities. We discuss its potential to improve access to large-scale, isotropic image segmentation and invite the community to explore and contribute to this open-source initiative.
Authors: Erwan Plouet, D\'edalo Sanz-Hern\'andez, Aymeric Vecchiola, Julie Grollier, Frank Mizrahi
Abstract: The ability to process time-series at low energy cost is critical for many applications. Recurrent neural network, which can perform such tasks, are computationally expensive when implementing in software on conventional computers. Here we propose to implement a recurrent neural network in hardware using spintronic oscillators as dynamical neurons. Using numerical simulations, we build a multi-layer network and demonstrate that we can use backpropagation through time (BPTT) and standard machine learning tools to train this network. Leveraging the transient dynamics of the spintronic oscillators, we solve the sequential digits classification task with $89.83\pm2.91~\%$ accuracy, as good as the equivalent software network. We devise guidelines on how to choose the time constant of the oscillators as well as hyper-parameters of the network to adapt to different input time scales.
Authors: Lang Zeng, Weijing Tang, Zhao Ren, Ying Ding
Abstract: Optimizing Cox regression and its neural network variants poses substantial computational challenges in large-scale studies. Stochastic gradient descent (SGD), known for its scalability in model optimization, has recently been adapted to optimize Cox models. Unlike its conventional application, which typically targets a sum of independent individual loss, SGD for Cox models updates parameters based on the partial likelihood of a subset of data. Despite its empirical success, the theoretical foundation for optimizing Cox partial likelihood with SGD is largely underexplored. In this work, we demonstrate that the SGD estimator targets an objective function that is batch-size-dependent. We establish that the SGD estimator for the Cox neural network (Cox-NN) is consistent and achieves the optimal minimax convergence rate up to a polylogarithmic factor. For Cox regression, we further prove the $\sqrt{n}$-consistency and asymptotic normality of the SGD estimator, with variance depending on the batch size. Furthermore, we quantify the impact of batch size on Cox-NN training and its effect on the SGD estimator's asymptotic efficiency in Cox regression. These findings are validated by extensive numerical experiments and provide guidance for selecting batch sizes in SGD applications. Finally, we demonstrate the effectiveness of SGD in a real-world application where GD is unfeasible due to the large scale of data.
Authors: Luciana Ferrer, Daniel Ramos
Abstract: Most machine learning classifiers are designed to output posterior probabilities for the classes given the input sample. These probabilities may be used to make the categorical decision on the class of the sample; provided as input to a downstream system; or provided to a human for interpretation. Evaluating the quality of the posteriors generated by these system is an essential problem which was addressed decades ago with the invention of proper scoring rules (PSRs). Unfortunately, much of the recent machine learning literature uses calibration metrics -- most commonly, the expected calibration error (ECE) -- as a proxy to assess posterior performance. The problem with this approach is that calibration metrics reflect only one aspect of the quality of the posteriors, ignoring the discrimination performance. For this reason, we argue that calibration metrics should play no role in the assessment of posterior quality. Expected PSRs should instead be used for this job, preferably normalized for ease of interpretation. In this work, we first give a brief review of PSRs from a practical perspective, motivating their definition using Bayes decision theory. We discuss why expected PSRs provide a principled measure of the quality of a system's posteriors and why calibration metrics are not the right tool for this job. We argue that calibration metrics, while not useful for performance assessment, may be used as diagnostic tools during system development. With this purpose in mind, we discuss a simple and practical calibration metric, called calibration loss, derived from a decomposition of expected PSRs. We compare this metric with the ECE and with the expected score divergence calibration metric from the PSR literature and argue, using theoretical and empirical evidence, that calibration loss is superior to these two metrics.
Authors: Ryan Aponte (Carnegie Mellon University), Ryan A. Rossi (Adobe Research), Shunan Guo (Adobe Research), Franck Dernoncourt (Adobe Research), Tong Yu (Adobe Research), Xiang Chen (Adobe Research), Subrata Mitra (Adobe Research), Nedim Lipka (Adobe Research)
Abstract: Large language models (LLMs) have been applied to a wide range of tasks, including text summarization, web navigation, and chatbots. They have benefitted from supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) following an unsupervised pretraining. These datasets can be difficult to collect, limited in scope, and vary in sample quality. Additionally, datasets can vary extensively in supervision format, from numerical to binary as well as multi-dimensional with many different values. We present a framework for fine-tuning LLMs using heterogeneous feedback, which has two main components. First, we combine the heterogeneous feedback data into a single supervision format, compatible with methods like SFT and RLHF. Next, given this unified feedback dataset, we extract a high-quality and diverse subset to obtain performance increases potentially exceeding the full dataset. We conduct extensive experiments to understand the effectiveness of these techniques for incorporating heterogeneous feedback, and demonstrate improvements from using a high-quality and diverse subset of the data. We find that our framework is able to improve models in multiple areas simultaneously, such as in instruction following and bias reduction.
Authors: Aishan Liu, Yuguang Zhou, Xianglong Liu, Tianyuan Zhang, Siyuan Liang, Jiakai Wang, Yanjun Pu, Tianlin Li, Junqi Zhang, Wenbo Zhou, Qing Guo, Dacheng Tao
Abstract: Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks described in abstract language into sequences of code snippets, which will serve as the execution logic for embodied agents. However, this paper uncovers a significant backdoor security threat within this process and introduces a novel method called \method{}. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM, prompting it to generate programs with context-dependent defects. These programs appear logically sound but contain defects that can activate and induce unintended behaviors when the operational agent encounters specific triggers in its interactive environment. To compromise the LLM's contextual environment, we employ adversarial in-context generation to optimize poisoned demonstrations, where an LLM judge evaluates these poisoned prompts, reporting to an additional LLM that iteratively optimizes the demonstration in a two-player adversarial game using chain-of-thought reasoning. To enable context-dependent behaviors in downstream agents, we implement a dual-modality activation strategy that controls both the generation and execution of program defects through textual and visual triggers. We expand the scope of our attack by developing five program defect modes that compromise key aspects of confidentiality, integrity, and availability in embodied agents. To validate the effectiveness of our approach, we conducted extensive experiments across various tasks, including robot planning, robot manipulation, and compositional visual reasoning. Additionally, we demonstrate the potential impact of our approach by successfully attacking real-world autonomous driving systems.
Authors: Dillon Bowen, Brendan Murphy, Will Cai, David Khachaturov, Adam Gleave, Kellin Pelrine
Abstract: Recent work shows that LLMs are vulnerable to data poisoning, in which they are trained on partially corrupted or harmful data. Poisoned data is hard to detect, breaks guardrails, and leads to undesirable and harmful behavior. Given the intense efforts by leading labs to train and deploy increasingly larger and more capable LLMs, it is critical to ask if the risk of data poisoning will be naturally mitigated by scale, or if it is an increasing threat. We consider three threat models by which data poisoning can occur: malicious fine-tuning, imperfect data curation, and intentional data contamination. Our experiments evaluate the effects of data poisoning on 23 frontier LLMs ranging from 1.5-72 billion parameters on three datasets which speak to each of our threat models. We find that larger LLMs are increasingly vulnerable, learning harmful behavior -- including sleeper agent behavior -- significantly more quickly than smaller LLMs with even minimal data poisoning. These results underscore the need for robust safeguards against data poisoning in larger LLMs.
Authors: Dylan Adams, Magda Zajaczkowska, Ashiq Anjum, Andrea Soltoggio, Shirin Dora
Abstract: Despite basic differences between Spiking Neural Networks (SNN) and Artificial Neural Networks (ANN), most research on SNNs involve adapting ANN-based methods for SNNs. Pruning (dropping connections) and quantization (reducing precision) are often used to improve energy efficiency of SNNs. These methods are very effective for ANNs whose energy needs are determined by signals transmitted on synapses. However, the event-driven paradigm in SNNs implies that energy is consumed by spikes. In this paper, we propose a new synapse model whose weights are modulated by Interspike Intervals (ISI) i.e. time difference between two spikes. SNNs composed of this synapse model, termed ISI Modulated SNNs (IMSNN), can use gradient descent to estimate how the ISI of a neuron changes after updating its synaptic parameters. A higher ISI implies fewer spikes and vice-versa. The learning algorithm for IMSNNs exploits this information to selectively propagate gradients such that learning is achieved by increasing the ISIs resulting in a network that generates fewer spikes. The performance of IMSNNs with dense and convolutional layers have been evaluated in terms of classification accuracy and the number of spikes using the MNIST and FashionMNIST datasets. The performance comparison with conventional SNNs shows that IMSNNs exhibit upto 90% reduction in the number of spikes while maintaining similar classification accuracy.
Authors: Zhanhao Zhao, Shaofeng Cai, Haotian Gao, Hexiang Pan, Siqi Xiang, Naili Xing, Gang Chen, Beng Chin Ooi, Yanyan Shen, Yuncheng Wu, Meihui Zhang
Abstract: Databases are increasingly embracing AI to provide autonomous system optimization and intelligent in-database analytics, aiming to relieve end-user burdens across various industry sectors. Nonetheless, most existing approaches fail to account for the dynamic nature of databases, which renders them ineffective for real-world applications characterized by evolving data and workloads. This paper introduces NeurDB, an AI-powered autonomous database that deepens the fusion of AI and databases with adaptability to data and workload drift. NeurDB establishes a new in-database AI ecosystem that seamlessly integrates AI workflows within the database. This integration enables efficient and effective in-database AI analytics and fast-adaptive learned system components. Empirical evaluations demonstrate that NeurDB substantially outperforms existing solutions in managing AI analytics tasks, with the proposed learned components more effectively handling environmental dynamism than state-of-the-art approaches.
Authors: Jiaqi Yao, Ding Liu
Abstract: This paper introduces an innovative and practical approach to universal quantum matrix multiplication. We designed optimized quantum adders and multipliers based on Quantum Fourier Transform (QFT), which significantly reduced the number of gates used compared to classical adders and multipliers. Subsequently, we construct a basic universal quantum matrix multiplication and extend it to the Strassen algorithm. We conduct comparative experiments to analyze the performance of the quantum matrix multiplication and evaluate the acceleration provided by the optimized quantum adder and multiplier. Furthermore, we investigate the advantages and disadvantages of the quantum Strassen algorithm compared to basic quantum matrix multiplication.
Authors: Siddhant Dutta, Nouhaila Innan, Alberto Marchisio, Sadok Ben Yahia, Muhammad Shafique
Abstract: Financial market prediction and optimal trading strategy development remain challenging due to market complexity and volatility. Our research in quantum finance and reinforcement learning for decision-making demonstrates the approach of quantum-classical hybrid algorithms to tackling real-world financial challenges. In this respect, we corroborate the concept with rigorous backtesting and validate the framework's performance under realistic market conditions, by including fixed transaction cost per trade. This paper introduces a Quantum Attention Deep Q-Network (QADQN) approach to address these challenges through quantum-enhanced reinforcement learning. Our QADQN architecture uses a variational quantum circuit inside a traditional deep Q-learning framework to take advantage of possible quantum advantages in decision-making. We gauge the QADQN agent's performance on historical data from major market indices, including the S&P 500. We evaluate the agent's learning process by examining its reward accumulation and the effectiveness of its experience replay mechanism. Our empirical results demonstrate the QADQN's superior performance, achieving better risk-adjusted returns with Sortino ratios of 1.28 and 1.19 for non-overlapping and overlapping test periods respectively, indicating effective downside risk management.
Authors: Johannes Schneider
Abstract: Large language models (LLM)'s are increasingly used for topic modeling outperforming classical topic models such as LDA. Commonly, pre-trained LLM encoders such as BERT are used out-of-the-box despite the fact that fine-tuning is known to improve LLMs considerably. The challenge lies in obtaining a suitable (labeled) dataset for fine-tuning. In this paper, we use the recent idea to use bag of sentences as the elementary unit in computing topics. In turn, we derive an approach FT-Topic to perform unsupervised fine-tuning relying primarily on two steps for constructing a training dataset in an automatic fashion. First, a heuristic method to identifies pairs of sentence groups that are either assumed to be of the same or different topics. Second, we remove sentence pairs that are likely labeled incorrectly. The dataset is then used to fine-tune an encoder LLM, which can be leveraged by any topic modeling approach using embeddings. However, in this work, we demonstrate its effectiveness by deriving a novel state-of-the-art topic modeling method called SenClu, which achieves fast inference through an expectation-maximization algorithm and hard assignments of sentence groups to a single topic, while giving users the possibility to encode prior knowledge on the topic-document distribution. Code is at \url{https://github.com/JohnTailor/FT-Topic}
Authors: Long Wei, Haodong Feng, Peiyan Hu, Tao Zhang, Yuchen Yang, Xiang Zheng, Ruiqi Feng, Dixia Fan, Tailin Wu
Abstract: The control problems of complex physical systems have wide applications in science and engineering. Several previous works have demonstrated that generative control methods based on diffusion models have significant advantages for solving these problems. However, existing generative control methods face challenges in handling closed-loop control, which is an inherent constraint for effective control of complex physical systems. In this paper, we propose a Closed-Loop Diffusion method for Physical systems Control (CL-DiffPhyCon). By adopting an asynchronous denoising schedule for different time steps, CL-DiffPhyCon generates control signals conditioned on real-time feedback from the environment. Thus, CL-DiffPhyCon is able to speed up diffusion control methods in a closed-loop framework. We evaluate CL-DiffPhyCon on the 1D Burgers' equation control and 2D incompressible fluid control tasks. The results demonstrate that CL-DiffPhyCon achieves notable control performance with significant sampling acceleration.
Authors: Yu Inatsu, Shion Takeno, Kentaro Kutsukake, Ichiro Takeuchi
Abstract: Level set estimation (LSE), the problem of identifying the set of input points where a function takes value above (or below) a given threshold, is important in practical applications. When the function is expensive-to-evaluate and black-box, the \textit{straddle} algorithm, which is a representative heuristic for LSE based on Gaussian process models, and its extensions having theoretical guarantees have been developed. However, many of existing methods include a confidence parameter $\beta^{1/2}_t$ that must be specified by the user, and methods that choose $\beta^{1/2}_t$ heuristically do not provide theoretical guarantees. In contrast, theoretically guaranteed values of $\beta^{1/2}_t$ need to be increased depending on the number of iterations and candidate points, and are conservative and not good for practical performance. In this study, we propose a novel method, the \textit{randomized straddle} algorithm, in which $\beta_t$ in the straddle algorithm is replaced by a random sample from the chi-squared distribution with two degrees of freedom. The confidence parameter in the proposed method has the advantages of not needing adjustment, not depending on the number of iterations and candidate points, and not being conservative. Furthermore, we show that the proposed method has theoretical guarantees that depend on the sample complexity and the number of iterations. Finally, we confirm the usefulness of the proposed method through numerical experiments using synthetic and real data.
Authors: Charles Brazier, Jean-Luc Rouas
Abstract: Large Language Models (LLMs) have shown remarkable performance in Natural Language Processing tasks, including Machine Translation (MT). In this work, we propose a novel MT pipeline that integrates emotion information extracted from a Speech Emotion Recognition (SER) model into LLMs to enhance translation quality. We first fine-tune five existing LLMs on the Libri-trans dataset and select the most performant model. Subsequently, we augment LLM prompts with different dimensional emotions and train the selected LLM under these different configurations. Our experiments reveal that integrating emotion information, especially arousal, into LLM prompts leads to notable improvements in translation quality.
Authors: Sho Ozaki, Shizuo Kaji, Toshikazu Imae, Kanabu Nawa, Hideomi Yamashita, Keiichi Nakagawa
Abstract: Image generative AI has garnered significant attention in recent years. In particular, the diffusion model, a core component of recent generative AI, produces high-quality images with rich diversity. In this study, we propose a novel CT reconstruction method by combining the denoising diffusion probabilistic model with iterative CT reconstruction. In sharp contrast to previous studies, we optimize the fidelity loss of CT reconstruction with respect to the latent variable of the diffusion model, instead of the image and model parameters. To suppress anatomical structure changes produced by the diffusion model, we shallow the diffusion and reverse processes, and fix a set of added noises in the reverse process to make it deterministic during inference. We demonstrate the effectiveness of the proposed method through sparse view CT reconstruction of 1/10 view projection data. Despite the simplicity of the implementation, the proposed method shows the capability of reconstructing high-quality images while preserving the patient's anatomical structure, and outperforms existing methods including iterative reconstruction, iterative reconstruction with total variation, and the diffusion model alone in terms of quantitative indices such as SSIM and PSNR. We also explore further sparse view CT using 1/20 view projection data with the same trained diffusion model. As the number of iterations increases, image quality improvement comparable to that of 1/10 sparse view CT reconstruction is achieved. In principle, the proposed method can be widely applied not only to CT but also to other imaging modalities such as MRI, PET, and SPECT.
Authors: Pranita Deshmukh, Nikita Kulkarni, Sanhita Kulkarni, Kareena Manghani, Raviraj Joshi
Abstract: With the surge in digital content in low-resource languages, there is an escalating demand for advanced Natural Language Processing (NLP) techniques tailored to these languages. BERT (Bidirectional Encoder Representations from Transformers), serving as the foundational framework for numerous NLP architectures and language models, is increasingly employed for the development of low-resource NLP models. Parameter Efficient Fine-Tuning (PEFT) is a method for fine-tuning Large Language Models (LLMs) and reducing the training parameters to some extent to decrease the computational costs needed for training the model and achieve results comparable to a fully fine-tuned model. In this work, we present a study of PEFT methods for the Indic low-resource language Marathi. We conduct a comprehensive analysis of PEFT methods applied to various monolingual and multilingual Marathi BERT models. These approaches are evaluated on prominent text classification datasets like MahaSent, MahaHate, and MahaNews. The incorporation of PEFT techniques is demonstrated to significantly expedite the training speed of the models, addressing a critical aspect of model development and deployment. In this study, we explore Low-Rank Adaptation of Large Language Models (LoRA) and adapter methods for low-resource text classification. We show that these methods are competitive with full fine-tuning and can be used without loss in accuracy. This study contributes valuable insights into the effectiveness of Marathi BERT models, offering a foundation for the continued advancement of NLP capabilities in Marathi and similar Indic languages.
Authors: Xingguang Yan, Han-Hung Lee, Ziyu Wan, Angel X. Chang
Abstract: We introduce a new approach for generating realistic 3D models with UV maps through a representation termed "Object Images." This approach encapsulates surface geometry, appearance, and patch structures within a 64x64 pixel image, effectively converting complex 3D shapes into a more manageable 2D format. By doing so, we address the challenges of both geometric and semantic irregularity inherent in polygonal meshes. This method allows us to use image generation models, such as Diffusion Transformers, directly for 3D shape generation. Evaluated on the ABO dataset, our generated shapes with patch structures achieve point cloud FID comparable to recent 3D generative models, while naturally supporting PBR material generation.
Authors: Matteo Lapucci, Davide Pucci
Abstract: In this paper, we deal with algorithms to solve the finite-sum problems related to fitting over-parametrized models, that typically satisfy the interpolation condition. In particular, we focus on approaches based on stochastic line searches and employing general search directions. We define conditions on the sequence of search directions that guarantee finite termination and bounds for the backtracking procedure. Moreover, we shed light on the additional property of directions needed to prove fast (linear) convergence of the general class of algorithms when applied to PL functions in the interpolation regime. From the point of view of algorithms design, the proposed analysis identifies safeguarding conditions that could be employed in relevant algorithmic framework. In particular, it could be of interest to integrate stochastic line searches within momentum, conjugate gradient or adaptive preconditioning methods.
Authors: Angie Boggust, Venkatesh Sivaraman, Yannick Assogba, Donghao Ren, Dominik Moritz, Fred Hohman
Abstract: To deploy machine learning models on-device, practitioners use compression algorithms to shrink and speed up models while maintaining their high-quality output. A critical aspect of compression in practice is model comparison, including tracking many compression experiments, identifying subtle changes in model behavior, and negotiating complex accuracy-efficiency trade-offs. However, existing compression tools poorly support comparison, leading to tedious and, sometimes, incomplete analyses spread across disjoint tools. To support real-world comparative workflows, we develop an interactive visual system called Compress and Compare. Within a single interface, Compress and Compare surfaces promising compression strategies by visualizing provenance relationships between compressed models and reveals compression-induced behavior changes by comparing models' predictions, weights, and activations. We demonstrate how Compress and Compare supports common compression analysis tasks through two case studies, debugging failed compression on generative language models and identifying compression artifacts in image classification models. We further evaluate Compress and Compare in a user study with eight compression experts, illustrating its potential to provide structure to compression workflows, help practitioners build intuition about compression, and encourage thorough analysis of compression's effect on model behavior. Through these evaluations, we identify compression-specific challenges that future visual analytics tools should consider and Compress and Compare visualizations that may generalize to broader model comparison tasks.
Authors: Boxi Cao, Mengjie Ren, Hongyu Lin, Xianpei Han, Feng Zhang, Junfeng Zhan, Le Sun
Abstract: Evaluation is the baton for the development of large language models. Current evaluations typically employ a single-item assessment paradigm for each atomic test objective, which struggles to discern whether a model genuinely possesses the required capabilities or merely memorizes/guesses the answers to specific questions. To this end, we propose a novel evaluation framework referred to as StructEval. Starting from an atomic test objective, StructEval deepens and broadens the evaluation by conducting a structured assessment across multiple cognitive levels and critical concepts, and therefore offers a comprehensive, robust and consistent evaluation for LLMs. Experiments on three widely-used benchmarks demonstrate that StructEval serves as a reliable tool for resisting the risk of data contamination and reducing the interference of potential biases, thereby providing more reliable and consistent conclusions regarding model capabilities. Our framework also sheds light on the design of future principled and trustworthy LLM evaluation protocols.
Authors: Rafael Sterzinger, Christian Stippel, Robert Sablatnig
Abstract: Etruscan mirrors constitute a significant category in Etruscan art, characterized by elaborate figurative illustrations featured on their backside. A laborious and costly aspect of their analysis and documentation is the task of manually tracing these illustrations. In previous work, a methodology has been proposed to automate this process, involving photometric-stereo scanning in combination with deep neural networks. While achieving quantitative performance akin to an expert annotator, some results still lack qualitative precision and, thus, require annotators for inspection and potential correction, maintaining resource intensity. In response, we propose a deep neural network trained to interactively refine existing annotations based on human guidance. Our human-in-the-loop approach streamlines annotation, achieving equal quality with up to 75% less manual input required. Moreover, during the refinement process, the relative improvement of our methodology over pure manual labeling reaches peak values of up to 26%, attaining drastically better quality quicker. By being tailored to the complex task of segmenting intricate lines, specifically distinguishing it from previous methods, our approach offers drastic improvements in efficacy, transferable to a broad spectrum of applications beyond Etruscan mirrors.
Authors: Naimeng Ye, Hanming Yang, Andrew Siah, Hongseok Namkoong
Abstract: Accurately gauging uncertainty on the underlying environment is a longstanding goal of intelligent systems. We characterize which latent concepts pre-trained sequence models are naturally able to reason with. We go back to De Finetti's predictive view of Bayesian reasoning: instead of modeling latent parameters through priors and likelihoods like topic models do, De Finetti has long advocated for modeling exchangeable (permutation invariant) sequences of observables. According to this view, pre-training autoregressive models formulates informed beliefs based on prior observations ("empirical Bayes"), and forward generation is a simulated instantiation of an environment ("posterior inference"). This connection allows extending in-context learning (ICL) beyond predictive settings, highlighting sequence models' ability to perform explicit statistical inference. In particular, we show the sequence prediction loss over exchangeable documents controls performance on downstream tasks where uncertainty quantification is key. Empirically, we propose and demonstrate several approaches for encoding exchangeability in sequence model architectures: data augmentation, regularization, and causal masking.
Authors: Siqiao Zhao, Zhikang Dong, Zeyu Cao, Raphael Douady
Abstract: When constructing portfolios, a key problem is that a lot of financial time series data are sparse, making it challenging to apply machine learning methods. Polymodel theory can solve this issue and demonstrate superiority in portfolio construction from various aspects. To implement the PolyModel theory for constructing a hedge fund portfolio, we begin by identifying an asset pool, utilizing over 10,000 hedge funds for the past 29 years' data. PolyModel theory also involves choosing a wide-ranging set of risk factors, which includes various financial indices, currencies, and commodity prices. This comprehensive selection mirrors the complexities of the real-world environment. Leveraging on the PolyModel theory, we create quantitative measures such as Long-term Alpha, Long-term Ratio, and SVaR. We also use more classical measures like the Sharpe ratio or Morningstar's MRAR. To enhance the performance of the constructed portfolio, we also employ the latest deep learning techniques (iTransformer) to capture the upward trend, while efficiently controlling the downside, using all the features. The iTransformer model is specifically designed to address the challenges in high-dimensional time series forecasting and could largely improve our strategies. More precisely, our strategies achieve better Sharpe ratio and annualized return. The above process enables us to create multiple portfolio strategies aiming for high returns and low risks when compared to various benchmarks.
Authors: Arsenii Mustafin, Alex Olshevsky, Ioannis Ch. Paschalidis
Abstract: Temporal difference (TD) learning is a policy evaluation in reinforcement learning whose performance can be enhanced by variance reduction methods. Recently, multiple works have sought to fuse TD learning with Stochastic Variance Reduced Gradient (SVRG) method to achieve a geometric rate of convergence. However, the resulting convergence rate is significantly weaker than what is achieved by SVRG in the setting of convex optimization. In this work we utilize a recent interpretation of TD-learning as the splitting of the gradient of an appropriately chosen function, thus simplifying the algorithm and fusing TD with SVRG. Our main result is a geometric convergence bound with predetermined learning rate of $1/8$, which is identical to the convergence bound available for SVRG in the convex setting. Our theoretical findings are supported by a set of experiments.
Authors: Xihong Yang, Erxue Min, Ke Liang, Yue Liu, Siwei Wang, Sihang Zhou, Huijun Wu, Xinwang Liu, En Zhu
Abstract: Contrastive deep graph clustering (CDGC) leverages the power of contrastive learning to group nodes into different clusters. The quality of contrastive samples is crucial for achieving better performance, making augmentation techniques a key factor in the process. However, the augmentation samples in existing methods are always predefined by human experiences, and agnostic from the downstream task clustering, thus leading to high human resource costs and poor performance. To overcome these limitations, we propose a Graph Node Clustering with Fully Learnable Augmentation, termed GraphLearner. It introduces learnable augmentors to generate high-quality and task-specific augmented samples for CDGC. GraphLearner incorporates two learnable augmentors specifically designed for capturing attribute and structural information. Moreover, we introduce two refinement matrices, including the high-confidence pseudo-label matrix and the cross-view sample similarity matrix, to enhance the reliability of the learned affinity matrix. During the training procedure, we notice the distinct optimization goals for training learnable augmentors and contrastive learning networks. In other words, we should both guarantee the consistency of the embeddings as well as the diversity of the augmented samples. To address this challenge, we propose an adversarial learning mechanism within our method. Besides, we leverage a two-stage training strategy to refine the high-confidence matrices. Extensive experimental results on six benchmark datasets validate the effectiveness of GraphLearner.The code and appendix of GraphLearner are available at https://github.com/xihongyang1999/GraphLearner on Github.
Authors: Haoyu Liu, Ningyi Liao, Siqiang Luo
Abstract: Graph neural networks (GNNs) realize great success in graph learning but suffer from performance loss when meeting heterophily, i.e. neighboring nodes are dissimilar, due to their local and uniform aggregation. Existing attempts of heterophilous GNNs incorporate long-range or global aggregations to distinguish nodes in the graph. However, these aggregations usually require iteratively maintaining and updating full-graph information, which limits their efficiency when applying to large-scale graphs. In this paper, we propose SIGMA, an efficient global heterophilous GNN aggregation integrating the structural similarity measurement SimRank. Our theoretical analysis illustrates that SIGMA inherently captures distant global similarity even under heterophily, that conventional approaches can only achieve after iterative aggregations. Furthermore, it enjoys efficient one-time computation with a complexity only linear to the node set size $\mathcal{O}(n)$. Comprehensive evaluation demonstrates that SIGMA achieves state-of-the-art performance with superior aggregation and overall efficiency. Notably, it obtains 5$\times$ acceleration on the large-scale heterophily dataset \emph{pokec} with over 30 million edges compared to the best baseline aggregation.
Authors: Kin G. Olivares, Geoffrey N\'egiar, Ruijun Ma, O. Nangba Meetei, Mengfei Cao, Michael W. Mahoney
Abstract: Obtaining accurate probabilistic forecasts is an important operational challenge in many applications, perhaps most obviously in energy management, climate forecasting, supply chain planning, and resource allocation. In many of these applications, there is a natural hierarchical structure over the forecasted quantities; and forecasting systems that adhere to this hierarchical structure are said to be coherent. Furthermore, operational planning benefits from accuracy at all levels of the aggregation hierarchy. Building accurate and coherent forecasting systems, however, is challenging: classic multivariate time series tools and neural network methods are still being adapted for this purpose. In this paper, we augment an MQForecaster neural network architecture with a novel deep Gaussian factor forecasting model that achieves coherence by construction, yielding a method we call the Deep Coherent Factor Model Neural Network (DeepCoFactor) model. DeepCoFactor generates samples that can be differentiated with respect to model parameters, allowing optimization on various sample-based learning objectives that align with the forecasting system's goals, including quantile loss and the scaled Continuous Ranked Probability Score (CRPS). In a comparison to state-of-the-art coherent forecasting methods, DeepCoFactor achieves significant improvements in scaled CRPS forecast accuracy, with gains between 4.16 and 54.40%, as measured on three publicly available hierarchical forecasting datasets.
Authors: Karuna Bhaila, Wen Huang, Yongkai Wu, Xintao Wu
Abstract: Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy protection in GNNs. In this work, we propose a learning framework that can provide node privacy at the user level, while incurring low utility loss. We focus on a decentralized notion of Differential Privacy, namely Local Differential Privacy, and apply randomization mechanisms to perturb both feature and label data at the node level before the data is collected by a central server for model training. Specifically, we investigate the application of randomization mechanisms in high-dimensional feature settings and propose an LDP protocol with strict privacy guarantees. Based on frequency estimation in statistical analysis of randomized data, we develop reconstruction methods to approximate features and labels from perturbed data. We also formulate this learning framework to utilize frequency estimates of graph clusters to supervise the training procedure at a sub-graph level. Extensive experiments on real-world and semi-synthetic datasets demonstrate the validity of our proposed model.
Authors: Paloma Sodhi, S. R. K. Branavan, Yoav Artzi, Ryan McDonald
Abstract: Performing tasks on the web presents fundamental challenges to large language models (LLMs), including combinatorially large open-world tasks and variations across web interfaces. Simply specifying a large prompt to handle all possible behaviors and states is extremely complex, and results in behavior leaks between unrelated behaviors. Decomposition to distinct policies can address this challenge, but requires carefully handing off control between policies. We propose Stacked LLM Policies for Web Actions (SteP), an approach to dynamically compose policies to solve a diverse set of web tasks. SteP defines a Markov Decision Process where the state is a stack of policies representing the control state, i.e., the chain of policy calls. Unlike traditional methods that are restricted to static hierarchies, SteP enables dynamic control that adapts to the complexity of the task. We evaluate SteP against multiple baselines and web environments including WebArena, MiniWoB++, and a CRM. On WebArena, SteP improves (14.9\% to 33.5\%) over SOTA that use GPT-4 policies, while on MiniWob++, SteP is competitive with prior works while using significantly less data. Our code and data are available at https://asappresearch.github.io/webagents-step.
Authors: Yunke Wang, Minjing Dong, Yukun Zhao, Bo Du, Chang Xu
Abstract: Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects.
Authors: Runqi Lin, Chaojian Yu, Bo Han, Tongliang Liu
Abstract: Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in both natural and adversarial training. Existing methods struggle to consistently address different types of overfitting, typically designing strategies that focus separately on either natural or adversarial patterns. In this work, we adopt a unified perspective by solely focusing on natural patterns to explore different types of overfitting. Specifically, we examine the memorization effect in DNNs and reveal a shared behaviour termed over-memorization, which impairs their generalization capacity. This behaviour manifests as DNNs suddenly becoming high-confidence in predicting certain training patterns and retaining a persistent memory for them. Furthermore, when DNNs over-memorize an adversarial pattern, they tend to simultaneously exhibit high-confidence prediction for the corresponding natural pattern. These findings motivate us to holistically mitigate different types of overfitting by hindering the DNNs from over-memorization training patterns. To this end, we propose a general framework, Distraction Over-Memorization (DOM), which explicitly prevents over-memorization by either removing or augmenting the high-confidence natural patterns. Extensive experiments demonstrate the effectiveness of our proposed method in mitigating overfitting across various training paradigms.
Authors: Theodor Westny, Arman Mohammadi, Daniel Jung, Erik Frisk
Abstract: This paper addresses the training of Neural Ordinary Differential Equations (neural ODEs), and in particular explores the interplay between numerical integration techniques, stability regions, step size, and initialization techniques. It is shown how the choice of integration technique implicitly regularizes the learned model, and how the solver's corresponding stability region affects training and prediction performance. From this analysis, a stability-informed parameter initialization technique is introduced. The effectiveness of the initialization method is displayed across several learning benchmarks and industrial applications.
Authors: Sangamesh Kodge, Gobinda Saha, Kaushik Roy
Abstract: Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion request, often constrained by computational limits and restricted data access. In this work, we introduce a novel class unlearning algorithm designed to strategically eliminate specific classes from the learned model. Our algorithm first estimates the Retain and the Forget Spaces using Singular Value Decomposition on the layerwise activations for a small subset of samples from the retain and unlearn classes, respectively. We then compute the shared information between these spaces and remove it from the forget space to isolate class-discriminatory feature space. Finally, we obtain the unlearned model by updating the weights to suppress the class discriminatory features from the activation spaces. We demonstrate our algorithm's efficacy on ImageNet using a Vision Transformer with only $\sim 1.5\%$ drop in retain accuracy compared to the original model while maintaining under $1\%$ accuracy on the unlearned class samples. Furthermore, our algorithm exhibits competitive unlearning performance and resilience against Membership Inference Attacks (MIA). Compared to baselines, it achieves an average accuracy improvement of $1.38\%$ on the ImageNet dataset while requiring up to $10 \times$ fewer samples for unlearning. Additionally, under stronger MIA attacks on the CIFAR-100 dataset using a ResNet18 architecture, our approach outperforms the best baseline by $1.8\%$. Our code is available at https://github.com/sangamesh-kodge/class_forgetting.
Authors: Karol Capa{\l}a, Paulina Tworek, Jose Sousa
Abstract: In a world where Machine Learning (ML) is increasingly deployed to support decision-making in critical domains, providing decision-makers with explainable, stable, and relevant inputs becomes fundamental. Understanding how machine learning works under missing data and how this affects feature variability is paramount. This is even more relevant as machine learning approaches focus on standardising decision-making approaches that rely on an idealised set of features. However, decision-making in human activities often relies on incomplete data, even in critical domains. This paper addresses this gap by conducting a set of experiments using traditional machine learning methods that look for optimal decisions in comparison to a recently deployed machine learning method focused on a classification that is more descriptive and mimics human decision making, allowing for the natural integration of explainability. We found that the ML descriptive approach maintains higher classification accuracy while ensuring the stability of feature selection as data incompleteness increases. This suggests that descriptive classification methods can be helpful in uncertain decision-making scenarios.
Authors: Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, Jos\'e Miguel Hern\'andez-Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A. Osborne, Tim G. J. Rudner, David R\"ugamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang
Abstract: In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.
Authors: Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Li\`o, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veli\v{c}kovi\'c, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi
Abstract: Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field.
Authors: Muhammad Kashif, Muhammad Shafique
Abstract: In this paper, we present a novel framework for enhancing the performance of Quanvolutional Neural Networks (QuNNs) by introducing trainable quanvolutional layers and addressing the critical challenges associated with them. Traditional quanvolutional layers, although beneficial for feature extraction, have largely been static, offering limited adaptability. Unlike state-of-the-art, our research overcomes this limitation by enabling training within these layers, significantly increasing the flexibility and potential of QuNNs. However, the introduction of multiple trainable quanvolutional layers induces complexities in gradient-based optimization, primarily due to the difficulty in accessing gradients across these layers. To resolve this, we propose a novel architecture, Residual Quanvolutional Neural Networks (ResQuNNs), leveraging the concept of residual learning, which facilitates the flow of gradients by adding skip connections between layers. By inserting residual blocks between quanvolutional layers, we ensure enhanced gradient access throughout the network, leading to improved training performance. Moreover, we provide empirical evidence on the strategic placement of these residual blocks within QuNNs. Through extensive experimentation, we identify an efficient configuration of residual blocks, which enables gradients across all the layers in the network that eventually results in efficient training. Our findings suggest that the precise location of residual blocks plays a crucial role in maximizing the performance gains in QuNNs. Our results mark a substantial step forward in the evolution of quantum deep learning, offering new avenues for both theoretical development and practical quantum computing applications.
Authors: Daniil Dmitriev, Krist\'of Szab\'o, Amartya Sanyal
Abstract: In this paper, we provide lower bounds for Differentially Private (DP) Online Learning algorithms. Our result shows that, for a broad class of $(\varepsilon,\delta)$-DP online algorithms, for number of rounds $T$ such that $\log T\leq O(1 / \delta)$, the expected number of mistakes incurred by the algorithm grows as $\Omega(\log \frac{T}{\delta})$. This matches the upper bound obtained by Golowich and Livni (2021) and is in contrast to non-private online learning where the number of mistakes is independent of $T$. To the best of our knowledge, our work is the first result towards settling lower bounds for DP-Online learning and partially addresses the open question in Sanyal and Ramponi (2022).
Authors: Jae-Won Chung, Nishil Talati, Mosharaf Chowdhury
Abstract: The "AI for Science, Energy, and Security" report from DOE outlines a significant focus on developing and optimizing artificial intelligence workflows for a foundational impact on a broad range of DOE missions. With the pervasive usage of artificial intelligence (AI) and machine learning (ML) tools and techniques, their energy efficiency is likely to become the gating factor toward adoption. This is because generative AI (GenAI) models are massive energy hogs: for instance, training a 200-billion parameter large language model (LLM) at Amazon is estimated to have taken 11.9 GWh, which is enough to power more than a thousand average U.S. households for a year. Inference consumes even more energy, because a model trained once serve millions. Given this scale, high energy efficiency is key to addressing the power delivery problem of constructing and operating new supercomputers and datacenters specialized for AI workloads. In that regard, we outline software- and architecture-level research challenges and opportunities, setting the stage for creating cross-layer energy optimizations in AI systems.
Authors: Evandro S. Ortigossa, F\'abio F. Dias, Brian Barr, Claudio T. Silva, Luis Gustavo Nonato
Abstract: The development of machine learning applications has increased significantly in recent years, motivated by the remarkable ability of learning-powered systems to discover and generalize intricate patterns hidden in massive datasets. Modern learning models, while powerful, often have a level of complexity that renders them opaque black boxes, resulting in a notable lack of transparency that hinders our ability to decipher their reasoning. Opacity challenges the interpretability and practical application of machine learning, especially in critical domains where understanding the underlying reasons is essential for informed decision-making. Explainable Artificial Intelligence (XAI) rises to address that challenge, unraveling the complexity of black boxes by providing elucidating explanations. Among the various XAI approaches, feature attribution/importance stands out for its capacity to delineate the significance of input features in the prediction process. However, most existing attribution methods have limitations, such as instability, when divergent explanations may result from similar or even the same instance. This work introduces T-Explainer, a novel local additive attribution explainer based on Taylor expansion. It has desirable properties, such as local accuracy and consistency, making T-Explainer stable over multiple runs. We demonstrate T-Explainer's effectiveness in quantitative benchmark experiments against well-known attribution methods. Additionally, we provide several tools to evaluate and visualize explanations, turning T-Explainer into a comprehensive XAI framework.
Authors: Nishad Singhi, Jae Myung Kim, Karsten Roth, Zeynep Akata
Abstract: Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allows for human interventions, in which expert users are given the ability to modify potentially misaligned concept choices to influence the decision behavior of the model in an interpretable fashion. However, existing approaches often require numerous human interventions per image to achieve strong performances, posing practical challenges in scenarios where obtaining human feedback is expensive. In this paper, we find that this is noticeably driven by an independent treatment of concepts during intervention, wherein a change of one concept does not influence the use of other ones in the model's final decision. To address this issue, we introduce a trainable concept intervention realignment module, which leverages concept relations to realign concept assignments post-intervention. Across standard, real-world benchmarks, we find that concept realignment can significantly improve intervention efficacy; significantly reducing the number of interventions needed to reach a target classification performance or concept prediction accuracy. In addition, it easily integrates into existing concept-based architectures without requiring changes to the models themselves. This reduced cost of human-model collaboration is crucial to enhancing the feasibility of CBMs in resource-constrained environments. Our code is available at: https://github.com/ExplainableML/concept_realignment.
Authors: Bettina Finzel, Patrick Hilme, Johannes Rabold, Ute Schmid
Abstract: Explanations for Convolutional Neural Networks (CNNs) based on relevance of input pixels might be too unspecific to evaluate which and how input features impact model decisions. Especially in complex real-world domains like biology, the presence of specific concepts and of relations between concepts might be discriminating between classes. Pixel relevance is not expressive enough to convey this type of information. In consequence, model evaluation is limited and relevant aspects present in the data and influencing the model decisions might be overlooked. This work presents a novel method to explain and evaluate CNN models, which uses a concept- and relation-based explainer (CoReX). It explains the predictive behavior of a model on a set of images by masking (ir-)relevant concepts from the decision-making process and by constraining relations in a learned interpretable surrogate model. We test our approach with several image data sets and CNN architectures. Results show that CoReX explanations are faithful to the CNN model in terms of predictive outcomes. We further demonstrate through a human evaluation that CoReX is a suitable tool for generating combined explanations that help assessing the classification quality of CNNs. We further show that CoReX supports the identification and re-classification of incorrect or ambiguous classifications.
Authors: Yusuke Yamazaki, Ali Harandi, Mayu Muramatsu, Alexandre Viardin, Markus Apel, Tim Brepols, Stefanie Reese, Shahed Rezaei
Abstract: We propose a novel finite element-based physics-informed operator learning framework that allows for predicting spatiotemporal dynamics governed by partial differential equations (PDEs). The proposed framework employs a loss function inspired by the finite element method (FEM) with the implicit Euler time integration scheme. A transient thermal conduction problem is considered to benchmark the performance. The proposed operator learning framework takes a temperature field at the current time step as input and predicts a temperature field at the next time step. The Galerkin discretized weak formulation of the heat equation is employed to incorporate physics into the loss function, which is coined finite operator learning (FOL). Upon training, the networks successfully predict the temperature evolution over time for any initial temperature field at high accuracy compared to the FEM solution. The framework is also confirmed to be applicable to a heterogeneous thermal conductivity and arbitrary geometry. The advantages of FOL can be summarized as follows: First, the training is performed in an unsupervised manner, avoiding the need for a large data set prepared from costly simulations or experiments. Instead, random temperature patterns generated by the Gaussian random process and the Fourier series, combined with constant temperature fields, are used as training data to cover possible temperature cases. Second, shape functions and backward difference approximation are exploited for the domain discretization, resulting in a purely algebraic equation. This enhances training efficiency, as one avoids time-consuming automatic differentiation when optimizing weights and biases while accepting possible discretization errors. Finally, thanks to the interpolation power of FEM, any arbitrary geometry can be handled with FOL, which is crucial to addressing various engineering application scenarios.
Authors: Viktor Martinek, Julia Reuter, Ophelia Frotscher, Sanaz Mostaghim, Markus Richter, Roland Herzog
Abstract: We study the addition of shape constraints (SC) and their consideration during the parameter identification step of symbolic regression (SR). SC serve as a means to introduce prior knowledge about the shape of the otherwise unknown model function into SR. Unlike previous works that have explored SC in SR, we propose minimizing SC violations during parameter identification using gradient-based numerical optimization. We test three algorithm variants to evaluate their performance in identifying three symbolic expressions from synthetically generated data sets. This paper examines two benchmark scenarios: one with varying noise levels and another with reduced amounts of training data. The results indicate that incorporating SC into the expression search is particularly beneficial when data is scarce. Compared to using SC only in the selection process, our approach of minimizing violations during parameter identification shows a statistically significant benefit in some of our test cases, without being significantly worse in any instance.
Authors: Danial Saber, Amirali Salehi-Abari
Abstract: Graph Neural Networks (GNNs) have emerged as the predominant method for analyzing graph-structured data. However, canonical GNNs have limited expressive power and generalization capability, thus triggering the development of more expressive yet computationally intensive methods. One such approach is to create a series of perturbed versions of input graphs and then repeatedly conduct multiple message-passing operations on all variations during training. Despite their expressive power, this approach does not scale well on larger graphs. To address this scalability issue, we introduce Scalable Expressiveness through Preprocessed Graph Perturbation (SE2P). This model offers a flexible, configurable balance between scalability and generalizability with four distinct configuration classes. At one extreme, the configuration prioritizes scalability through minimal learnable feature extraction and extensive preprocessing; at the other extreme, it enhances generalizability with more learnable feature extractions, though this increases scalability costs. We conduct extensive experiments on real-world datasets to evaluate the generalizability and scalability of SE2P variants compared to various state-of-the-art benchmarks. Our results indicate that, depending on the chosen SE2P configuration, the model can enhance generalizability compared to benchmarks while achieving significant speed improvements of up to 8-fold.
Authors: Hannah Brown, Leon Lin, Kenji Kawaguchi, Michael Shieh
Abstract: We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inputs and outputs of a generator model, significantly reducing the cost of implementation in comparison to other, finetuning-based methods. Our method can significantly reduce the attack success rate of attacks on both open and closed-source LLMs, beyond the reductions demonstrated by Llama-Guard2 and commonly used content moderation APIs. We present an analysis of the effectiveness of our method, including attempts to attack the evaluator in various settings, demonstrating that it is also more resilient to attacks than existing methods. Code and data will be made available at https://github.com/Linlt-leon/self-eval.
Authors: Wei Jiang, Tong Chen, Guanhua Ye, Wentao Zhang, Lizhen Cui, Zi Huang, Hongzhi Yin
Abstract: Urban flow prediction is a spatio-temporal modeling task that estimates the throughput of transportation services like buses, taxis, and ride-sharing, where data-driven models have become the most popular solution in the past decade. Meanwhile, the implicitly learned mapping between historical observations to the prediction targets tend to over-simplify the dynamics of real-world urban flows, leading to suboptimal predictions. Some recent spatio-temporal prediction solutions bring remedies with the notion of physics-guided machine learning (PGML), which describes spatio-temporal data with nuanced and principled physics laws, thus enhancing both the prediction accuracy and interpretability. However, these spatio-temporal PGML methods are built upon a strong assumption that the observed data fully conforms to the differential equations that define the physical system, which can quickly become ill-posed in urban flow prediction tasks. The observed urban flow data, especially when sliced into time-dependent snapshots to facilitate predictions, is typically incomplete and sparse, and prone to inherent noise incurred in the collection process. As a result, such physical inconsistency between the data and PGML model significantly limits the predictive power and robustness of the solution. Moreover, due to the interval-based predictions and intermittent nature of data filing in many transportation services, the instantaneous dynamics of urban flows can hardly be captured, rendering differential equation-based continuous modeling a loose fit for this setting. To overcome the challenges, we develop a discretized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR) to enhance PN. Experimental results in four real-world datasets demonstrate that our method achieves state-of-the-art performance with a demonstrable improvement in robustness.
Authors: Tianyu Xiong, Skylar W. Wurster, Hanqi Guo, Tom Peterka, Han-Wei Shen
Abstract: Feature grid Scene Representation Networks (SRNs) have been applied to scientific data as compact functional surrogates for analysis and visualization. As SRNs are black-box lossy data representations, assessing the prediction quality is critical for scientific visualization applications to ensure that scientists can trust the information being visualized. Currently, existing architectures do not support inference time reconstruction quality assessment, as coordinate-level errors cannot be evaluated in the absence of ground truth data. We propose a parameter-efficient multi-decoder SRN (MDSRN) ensemble architecture consisting of a shared feature grid with multiple lightweight multi-layer perceptron decoders. MDSRN can generate a set of plausible predictions for a given input coordinate to compute the mean as the prediction of the multi-decoder ensemble and the variance as a confidence score. The coordinate-level variance can be rendered along with the data to inform the reconstruction quality, or be integrated into uncertainty-aware volume visualization algorithms. To prevent the misalignment between the quantified variance and the prediction quality, we propose a novel variance regularization loss for ensemble learning that promotes the Regularized multi-decoder SRN (RMDSRN) to obtain a more reliable variance that correlates closely to the true model error. We comprehensively evaluate the quality of variance quantification and data reconstruction of Monte Carlo Dropout, Mean Field Variational Inference, Deep Ensemble, and Predicting Variance compared to the proposed MDSRN and RMDSRN across diverse scalar field datasets. We demonstrate that RMDSRN attains the most accurate data reconstruction and competitive variance-error correlation among uncertain SRNs under the same neural network parameter budgets.
Authors: Xianliang Xu, Ting Du, Wang Kong, Ye Li, Zhongyi Huang
Abstract: First-order methods, such as gradient descent (GD) and stochastic gradient descent (SGD), have been proven effective in training neural networks. In the context of over-parameterization, there is a line of work demonstrating that randomly initialized (stochastic) gradient descent converges to a globally optimal solution at a linear convergence rate for the quadratic loss function. However, the learning rate of GD for training two-layer neural networks exhibits poor dependence on the sample size and the Gram matrix, leading to a slow training process. In this paper, we show that for the $L^2$ regression problems, the learning rate can be improved from $\mathcal{O}(\lambda_0/n^2)$ to $\mathcal{O}(1/\|\bm{H}^{\infty}\|_2)$, which implies that GD actually enjoys a faster convergence rate. Furthermore, we generalize the method to GD in training two-layer Physics-Informed Neural Networks (PINNs), showing a similar improvement for the learning rate. Although the improved learning rate has a mild dependence on the Gram matrix, we still need to set it small enough in practice due to the unknown eigenvalues of the Gram matrix. More importantly, the convergence rate is tied to the least eigenvalue of the Gram matrix, which can lead to slow convergence. In this work, we provide the convergence analysis of natural gradient descent (NGD) in training two-layer PINNs, demonstrating that the learning rate can be $\mathcal{O}(1)$, and at this rate, the convergence rate is independent of the Gram matrix.
Authors: Olga Ovcharenko, Rita Sevastjanova, Valentina Boeva
Abstract: Humans struggle to perceive and interpret high-dimensional data. Therefore, high-dimensional data are often projected into two dimensions for visualization. Many applications benefit from complex nonlinear dimensionality reduction techniques, but the effects of individual high-dimensional features are hard to explain in the two-dimensional space. Most visualization solutions use multiple two-dimensional plots, each showing the effect of one high-dimensional feature in two dimensions; this approach creates a need for a visual inspection of k plots for a k-dimensional input space. Our solution, Feature Clock, provides a novel approach that eliminates the need to inspect these k plots to grasp the influence of original features on the data structure depicted in two dimensions. Feature Clock enhances the explainability and compactness of visualizations of embedded data and is available in an open-source Python library.
Authors: Sifat Ut Taki, Arthi Padmanabhan, Spyridon Mastorakis
Abstract: Nowadays, cloud-based services are widely favored over the traditional approach of locally training a Neural Network (NN) model. Oftentimes, a cloud service processes multiple requests from users--thus training multiple NN models concurrently. However, training NN models concurrently is a challenging process, which typically requires significant amounts of available computing resources and takes a long time to complete. In this paper, we present UnifiedNN to effectively train multiple NN models concurrently on the cloud. UnifiedNN effectively "combines" multiple NN models and features several memory and time conservation mechanisms to train multiple NN models simultaneously without impacting the accuracy of the training process. Specifically, UnifiedNN merges multiple NN models and creates a large singular unified model in order to efficiently train all models at once. We have implemented a prototype of UnifiedNN in PyTorch and we have compared its performance with relevant state-of-the-art frameworks. Our experimental results demonstrate that UnifiedNN can reduce memory consumption by up to 53% and training time by up to 81% when compared with vanilla PyTorch without impacting the model training and testing accuracy. Finally, our results indicate that UnifiedNN can reduce memory consumption by up to 52% and training time by up to 41% when compared to state-of-the-art frameworks when training multiple models concurrently.
Authors: Zhi-Song Liu, Petri Clusius, Michael Boy
Abstract: Modeling atmospheric chemistry is complex and computationally intense. Given the recent success of Deep neural networks in digital signal processing, we propose a Neural Network Emulator for fast chemical concentration modeling. We consider atmospheric chemistry as a time-dependent Ordinary Differential Equation. To extract the hidden correlations between initial states and future time evolution, we propose ChemNNE, an Attention based Neural Network Emulator (NNE) that can model the atmospheric chemistry as a neural ODE process. To efficiently simulate the chemical changes, we propose the sinusoidal time embedding to estimate the oscillating tendency over time. More importantly, we use the Fourier neural operator to model the ODE process for efficient computation. We also propose three physical-informed losses to supervise the training optimization. To evaluate our model, we propose a large-scale chemical dataset that can be used for neural network training and evaluation. The extensive experiments show that our approach achieves state-of-the-art performance in modeling accuracy and computational speed.
Authors: Lixiang Zhang, Lin Lin, Jia Li
Abstract: The architectures of deep neural networks (DNN) rely heavily on the underlying grid structure of variables, for instance, the lattice of pixels in an image. For general high dimensional data with variables not associated with a grid, the multi-layer perceptron and deep belief network are often used. However, it is frequently observed that those networks do not perform competitively and they are not helpful for identifying important variables. In this paper, we propose a framework that imposes on blocks of variables a chain structure obtained by step-wise greedy search so that the DNN architecture can leverage the constructed grid. We call this new neural network Deep Variable-Block Chain (DVC). Because the variable blocks are used for classification in a sequential manner, we further develop the capacity of selecting variables adaptively according to a number of regions trained by a decision tree. Our experiments show that DVC outperforms other generic DNNs and other strong classifiers. Moreover, DVC can achieve high accuracy at much reduced dimensionality and sometimes reveals drastically different sets of relevant variables for different regions.
Authors: Robert Lefringhausen, Supitsana Srithasan, Armin Lederer, Sandra Hirche
Abstract: As control engineering methods are applied to increasingly complex systems, data-driven approaches for system identification appear as a promising alternative to physics-based modeling. While the Bayesian approaches prevalent for safety-critical applications usually rely on the availability of state measurements, the states of a complex system are often not directly measurable. It may then be necessary to jointly estimate the dynamics and the latent state, making the quantification of uncertainties and the design of controllers with formal performance guarantees considerably more challenging. This paper proposes a novel method for the computation of an optimal input trajectory for unknown nonlinear systems with latent states based on a combination of particle Markov chain Monte Carlo methods and scenario theory. Probabilistic performance guarantees are derived for the resulting input trajectory, and an approach to validate the performance of arbitrary control laws is presented. The effectiveness of the proposed method is demonstrated in a numerical simulation.
Authors: Suprim Nakarmi, Sanam Pudasaini, Safal Thapaliya, Pratima Upretee, Retina Shrestha, Basant Giri, Bhanu Bhakta Neupane, Bishesh Khanal
Abstract: The consumption of microbial-contaminated food and water is responsible for the deaths of millions of people annually. Smartphone-based microscopy systems are portable, low-cost, and more accessible alternatives for the detection of Giardia and Cryptosporidium than traditional brightfield microscopes. However, the images from smartphone microscopes are noisier and require manual cyst identification by trained technicians, usually unavailable in resource-limited settings. Automatic detection of (oo)cysts using deep-learning-based object detection could offer a solution for this limitation. We evaluate the performance of four state-of-the-art object detectors to detect (oo)cysts of Giardia and Cryptosporidium on a custom dataset that includes both smartphone and brightfield microscopic images from vegetable samples. Faster RCNN, RetinaNet, You Only Look Once (YOLOv8s), and Deformable Detection Transformer (Deformable DETR) deep-learning models were employed to explore their efficacy and limitations. Our results show that while the deep-learning models perform better with the brightfield microscopy image dataset than the smartphone microscopy image dataset, the smartphone microscopy predictions are still comparable to the prediction performance of non-experts. Also, we publicly release brightfield and smartphone microscopy datasets with the benchmark results for the detection of Giardia and Cryptosporidium, independently captured on reference (or standard lab setting) and vegetable samples. Our code and dataset are available at https://github.com/naamiinepal/smartphone_microscopy and https://doi.org/10.5281/zenodo.7813183, respectively.
URLs: https://github.com/naamiinepal/smartphone_microscopy, https://doi.org/10.5281/zenodo.7813183,
Authors: Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding, Ganqu Cui, Zheni Zeng, Yufei Huang, Chaojun Xiao, Chi Han, Yi Ren Fung, Yusheng Su, Huadong Wang, Cheng Qian, Runchu Tian, Kunlun Zhu, Shihao Liang, Xingyu Shen, Bokai Xu, Zhen Zhang, Yining Ye, Bowen Li, Ziwei Tang, Jing Yi, Yuzhang Zhu, Zhenning Dai, Lan Yan, Xin Cong, Yaxi Lu, Weilin Zhao, Yuxiang Huang, Junxi Yan, Xu Han, Xian Sun, Dahai Li, Jason Phang, Cheng Yang, Tongshuang Wu, Heng Ji, Zhiyuan Liu, Maosong Sun
Abstract: Humans possess an extraordinary ability to create and utilize tools, allowing them to overcome physical limitations and explore new frontiers. With the advent of foundation models, AI systems have the potential to be equally adept in tool use as humans. This paradigm, i.e., tool learning with foundation models, combines the strengths of specialized tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. Despite its immense potential, there is still a lack of a comprehensive understanding of key challenges, opportunities, and future endeavors in this field. To this end, we present a systematic investigation of tool learning in this paper. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research into tool-augmented and tool-oriented learning. We formulate a general tool learning framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate the generalization in tool learning. Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools. Finally, we discuss several open problems that require further investigation for tool learning. In general, we hope this paper could inspire future research in integrating tools with foundation models.
Authors: Sebastian Peitz, Hans Harder, Feliks N\"uske, Friedrich Philipp, Manuel Schaller, Karl Worthmann
Abstract: The Koopman operator has become an essential tool for data-driven analysis, prediction and control of complex systems. The main reason is the enormous potential of identifying linear function space representations of nonlinear dynamics from measurements. This equally applies to ordinary, stochastic, and partial differential equations (PDEs). Until now, with a few exceptions only, the PDE case is mostly treated rather superficially, and the specific structure of the underlying dynamics is largely ignored. In this paper, we show that symmetries in the system dynamics can be carried over to the Koopman operator, which allows us to massively increase the model efficacy. Moreover, the situation where we only have access to partial observations (i.e., measurements, as is very common for experimental data) has not been treated to its full extent, either. Moreover, we address the highly-relevant case where we cannot measure the full state, such that alternative approaches such as delay coordinates have to be considered. We derive rigorous statements on the required number of observables in this situation, based on embedding theory. We present numerical evidence using various numerical examples including the wave equation and the Kuramoto-Sivashinsky equation.
Authors: Cheik Traor\'e, Vassilis Apidopoulos, Saverio Salzo, Silvia Villa
Abstract: In the context of finite sums minimization, variance reduction techniques are widely used to improve the performance of state-of-the-art stochastic gradient methods. Their practical impact is clear, as well as their theoretical properties. Stochastic proximal point algorithms have been studied as an alternative to stochastic gradient algorithms since they are more stable with respect to the choice of the step size. However, their variance-reduced versions are not as well studied as the gradient ones. In this work, we propose the first unified study of variance reduction techniques for stochastic proximal point algorithms. We introduce a generic stochastic proximal-based algorithm that can be specified to give the proximal version of SVRG, SAGA, and some of their variants. For this algorithm, in the smooth setting, we provide several convergence rates for the iterates and the objective function values, which are faster than those of the vanilla stochastic proximal point algorithm. More specifically, for convex functions, we prove a sublinear convergence rate of $O(1/k)$. In addition, under the Polyak-{\L}ojasiewicz (PL) condition, we obtain linear convergence rates. Finally, our numerical experiments demonstrate the advantages of the proximal variance reduction methods over their gradient counterparts in terms of the stability with respect to the choice of the step size in most cases, especially for difficult problems.
Authors: Santiago Rivier, Carlos Hinojosa, Silvio Giancola, Bernard Ghanem
Abstract: Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have significantly improved satellite image segmentation. However, most of these methods are typically trained in fully supervised settings that require high-quality pixel-level annotations, which are expensive and time-consuming to obtain. In this work, we present a weakly supervised learning algorithm to train semantic segmentation algorithms that only rely on query point annotations instead of full mask labels. Our proposed approach performs accurate semantic segmentation and improves efficiency by significantly reducing the cost and time required for manual annotation. Specifically, we generate superpixels and extend the query point labels into those superpixels that group similar meaningful semantics. Then, we train semantic segmentation models supervised with images partially labeled with the superpixel pseudo-labels. We benchmark our weakly supervised training approach on an aerial image dataset and different semantic segmentation architectures, showing that we can reach competitive performance compared to fully supervised training while reducing the annotation effort. The code of our proposed approach is publicly available at: https://github.com/santiago2205/LSSQPS.
Authors: Kenneth Allen, Ming-Jun Lai, Zhaiming Shen
Abstract: We study the classic matrix cross approximation based on the maximal volume submatrices. Our main results consist of an improvement of the classic estimate for matrix cross approximation and a greedy approach for finding the maximal volume submatrices. More precisely, we present a new proof of the classic estimate of the inequality with an improved constant. Also, we present a family of greedy maximal volume algorithms to improve the computational efficiency of matrix cross approximation. The proposed algorithms are shown to have theoretical guarantees of convergence. Finally, we present two applications: image compression and the least squares approximation of continuous functions. Our numerical results at the end of the paper demonstrate the effective performance of our approach.
Authors: Joshua Rosaler, Dhruv Desai, Bhaskarjit Sarmah, Dimitrios Vamvourellis, Deran Onay, Dhagash Mehta, Stefano Pasquali
Abstract: We initiate a novel approach to explain the predictions and out of sample performance of random forest (RF) regression and classification models by exploiting the fact that any RF can be mathematically formulated as an adaptive weighted K nearest-neighbors model. Specifically, we employ a recent result that, for both regression and classification tasks, any RF prediction can be rewritten exactly as a weighted sum of the training targets, where the weights are RF proximities between the corresponding pairs of data points. We show that this linearity facilitates a local notion of explainability of RF predictions that generates attributions for any model prediction across observations in the training set, and thereby complements established feature-based methods like SHAP, which generate attributions for a model prediction across input features. We show how this proximity-based approach to explainability can be used in conjunction with SHAP to explain not just the model predictions, but also out-of-sample performance, in the sense that proximities furnish a novel means of assessing when a given model prediction is more or less likely to be correct. We demonstrate this approach in the modeling of US corporate bond prices and returns in both regression and classification cases.
Authors: Sehmimul Hoque (Perimeter Institute for Theoretical Physics), Hao Jia (Department of Physics and Astronomy, University of British Columbia), Abhishek Abhishek (TRIUMF), Mojde Fadaie (Perimeter Institute for Theoretical Physics), J. Quetzalcoatl Toledo-Mar\'in (TRIUMF), Tiago Vale (Department of Physics, Simon Fraser University), Roger G. Melko (Perimeter Institute for Theoretical Physics), Maximilian Swiatlowski (TRIUMF), Wojciech T. Fedorko (TRIUMF)
Abstract: The Large Hadron Collider's high luminosity era presents major computational challenges in the analysis of collision events. Large amounts of Monte Carlo (MC) simulation will be required to constrain the statistical uncertainties of the simulated datasets below these of the experimental data. Modelling of high-energy particles propagating through the calorimeter section of the detector is the most computationally intensive MC simulation task. We introduce a technique combining recent advancements in generative models and quantum annealing for fast and efficient simulation of high-energy particle-calorimeter interactions.
Authors: Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang
Abstract: Large Language Models (LLMs) have already gained widespread adoption in software engineering, particularly in code generation tasks. However, updating these models with new knowledge can be prohibitively expensive, yet it is essential to maximize their utility, such as implementing a hotfix technique to address urgent or critical LLM errors. In this paper, we propose \textsc{MENT}, a novel and effective model editing approach to repair LLMs in coding tasks. \textsc{MENT} is effective, efficient, and reliable, capable of correcting a neural model by patching just one or two neurons. As pioneering work on neuron-level model editing of generative models, we formalize the editing process and introduce the involved concepts. We also introduce new measures to evaluate its generalization ability and establish a benchmark for further study. Our approach is evaluated on three coding tasks: line-level code generation, shellcode generation, and intent-to-bash translation. The experimental results demonstrate that the proposed approach significantly outperforms the state-of-the-art in both effectiveness and efficiency measures. Furthermore, we showcase the applications of \textsc{MENT} for LLM reasoning in software engineering. By editing LLM knowledge, the directly or indirectly dependent behaviors of API invocation in the chain-of-thought change accordingly. This illustrates the significance of repairing LLMs in the context of software engineering.
Authors: Zhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur Gretton
Abstract: We present the first optimal rates for infinite-dimensional vector-valued ridge regression on a continuous scale of norms that interpolate between $L_2$ and the hypothesis space, which we consider as a vector-valued reproducing kernel Hilbert space. These rates allow to treat the misspecified case in which the true regression function is not contained in the hypothesis space. We combine standard assumptions on the capacity of the hypothesis space with a novel tensor product construction of vector-valued interpolation spaces in order to characterize the smoothness of the regression function. Our upper bound not only attains the same rate as real-valued kernel ridge regression, but also removes the assumption that the target regression function is bounded. For the lower bound, we reduce the problem to the scalar setting using a projection argument. We show that these rates are optimal in most cases and independent of the dimension of the output space. We illustrate our results for the special case of vector-valued Sobolev spaces.
Authors: Gianpaolo Palo, Luigi Fiorillo, Giuliana Monachino, Michal Bechny, Michel Walti, Elias Meier, Francesca Pentimalli Biscaretti di Ruffia, Mark Melnykowycz, Athina Tzovara, Valentina Agostini, Francesca Dalia Faraci
Abstract: Study Objectives: Polysomnography (PSG) currently serves as the benchmark for evaluating sleep disorders. Its discomfort makes long-term monitoring unfeasible, leading to bias in sleep quality assessment. Hence, less invasive, cost-effective, and portable alternatives need to be explored. One promising contender is the in-ear-EEG sensor. This study aims to establish a methodology to assess the similarity between the single-channel in-ear-EEG and standard PSG derivations. Methods: The study involves four-hour signals recorded from ten healthy subjects aged 18 to 60 years. Recordings are analyzed following two complementary approaches: (i) a hypnogram-based analysis aimed at assessing the agreement between PSG and in-ear-EEG-derived hypnograms; and (ii) a feature-based analysis based on time- and frequency- domain feature extraction, unsupervised feature selection, and definition of Feature-based Similarity Index via Jensen-Shannon Divergence (JSD-FSI). Results: We find large variability between PSG and in-ear-EEG hypnograms scored by the same sleep expert according to Cohen's kappa metric, with significantly greater agreements for PSG scorers than for in-ear-EEG scorers (p < 0.001) based on Fleiss' kappa metric. On average, we demonstrate a high similarity between PSG and in-ear-EEG signals in terms of JSD-FSI (0.79 +/- 0.06 -awake, 0.77 +/- 0.07 -NREM, and 0.67 +/- 0.10 -REM) and in line with the similarity values computed independently on standard PSG-channel-combinations. Conclusions: In-ear-EEG is a valuable solution for home-based sleep monitoring, however further studies with a larger and more heterogeneous dataset are needed.
Authors: Arhan Jain, Alec Bunn, Austin Pham, TJ Tsai
Abstract: This article motivates, describes, and presents the PBSCR dataset for studying composer recognition of classical piano music. Our goal was to design a dataset that facilitates large-scale research on composer recognition that is suitable for modern architectures and training practices. To achieve this goal, we utilize the abundance of sheet music images and rich metadata on IMSLP, use a previously proposed feature representation called a bootleg score to encode the location of noteheads relative to staff lines, and present the data in an extremely simple format (2D binary images) to encourage rapid exploration and iteration. The dataset itself contains 40,000 62x64 bootleg score images for a 9-class recognition task, 100,000 62x64 bootleg score images for a 100-class recognition task, and 29,310 unlabeled variable-length bootleg score images for pretraining. The labeled data is presented in a form that mirrors MNIST images, in order to make it extremely easy to visualize, manipulate, and train models in an efficient manner. We include relevant information to connect each bootleg score image with its underlying raw sheet music image, and we scrape, organize, and compile metadata from IMSLP on all piano works to facilitate multimodal research and allow for convenient linking to other datasets. We release baseline results in a supervised and low-shot setting for future works to compare against, and we discuss open research questions that the PBSCR data is especially well suited to facilitate research on.
Authors: Yizhak Elboher, Raya Elsaleh, Omri Isac, M\'elanie Ducoffe, Audrey Galametz, Guillaume Pov\'eda, Ryma Boumazouza, No\'emie Cohen, Guy Katz
Abstract: As deep neural networks (DNNs) are becoming the prominent solution for many computational problems, the aviation industry seeks to explore their potential in alleviating pilot workload and in improving operational safety. However, the use of DNNs in this type of safety-critical applications requires a thorough certification process. This need can be addressed through formal verification, which provides rigorous assurances -- e.g.,~by proving the absence of certain mispredictions. In this case-study paper, we demonstrate this process using an image-classifier DNN currently under development at Airbus and intended for use during the aircraft taxiing phase. We use formal methods to assess this DNN's robustness to three common image perturbation types: noise, brightness and contrast, and some of their combinations. This process entails multiple invocations of the underlying verifier, which might be computationally expensive; and we therefore propose a method that leverages the monotonicity of these robustness properties, as well as the results of past verification queries, in order to reduce the overall number of verification queries required by nearly 60%. Our results provide an indication of the level of robustness achieved by the DNN classifier under study, and indicate that it is considerably more vulnerable to noise than to brightness or contrast perturbations.
Authors: Duo Wu, Xianda Wang, Yaqi Qiao, Zhi Wang, Junchen Jiang, Shuguang Cui, Fangxin Wang
Abstract: Many networking tasks now employ deep learning (DL) to solve complex prediction and optimization problems. However, current design philosophy of DL-based algorithms entails intensive engineering overhead due to the manual design of deep neural networks (DNNs) for different networking tasks. Besides, DNNs tend to achieve poor generalization performance on unseen data distributions/environments. Motivated by the recent success of large language models (LLMs), this work studies the LLM adaptation for networking to explore a more sustainable design philosophy. With the powerful pre-trained knowledge, the LLM is promising to serve as the foundation model to achieve "one model for all tasks" with even better performance and stronger generalization. In pursuit of this vision, we present NetLLM, the first framework that provides a coherent design to harness the powerful capabilities of LLMs with low efforts to solve networking problems. Specifically, NetLLM empowers the LLM to effectively process multimodal data in networking and efficiently generate task-specific answers. Besides, NetLLM drastically reduces the costs of fine-tuning the LLM to acquire domain knowledge for networking. Across three networking-related use cases - viewport prediction, adaptive bitrate streaming and cluster job scheduling, we showcase that the NetLLM-adapted LLM significantly outperforms state-of-the-art algorithms.
Authors: Bo Pan, Zheng Zhang, Yifei Zhang, Yuntong Hu, Liang Zhao
Abstract: Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large language models (LLMs) have recently demonstrated remarkable capabilities in few-shot and zero-shot TAG learning, but they suffer from scalability, cost, and privacy issues. Therefore, in this work, we focus on synergizing LLMs and graph models with their complementary strengths by distilling the power of LLMs to a local graph model on TAG learning. To address the inherent gaps between LLMs (generative models for texts) and graph models (discriminative models for graphs), we propose first to let LLMs teach an interpreter with rich textual rationale and then let a student model mimic the interpreter's reasoning without LLMs' textual rationale. Extensive experiments validate the efficacy of our proposed framework.
Authors: Daniel Schug, Tyler J. Kovach, M. A. Wolfe, Jared Benson, Sanghyeok Park, J. P. Dodson, J. Corrigan, M. A. Eriksson, Justyna P. Zwolak
Abstract: The rapid development of quantum dot (QD) devices for quantum computing has necessitated more efficient and automated methods for device characterization and tuning. Many of the measurements acquired during the tuning process come in the form of images that need to be properly analyzed to guide the subsequent tuning steps. By design, features present in such images capture certain behaviors or states of the measured QD devices. When considered carefully, such features can aid the control and calibration of QD devices. An important example of such images are so-called \textit{triangle plots}, which visually represent current flow and reveal characteristics important for QD device calibration. While image-based classification tools, such as convolutional neural networks (CNNs), can be used to verify whether a given measurement is \textit{good} and thus warrants the initiation of the next phase of tuning, they do not provide any insights into how the device should be adjusted in the case of \textit{bad} images. This is because CNNs sacrifice prediction and model intelligibility for high accuracy. To ameliorate this trade-off, a recent study introduced an image vectorization approach that relies on the Gabor wavelet transform [1]. Here we propose an alternative vectorization method that involves mathematical modeling of synthetic triangles to mimic the experimental data. Using explainable boosting machines, we show that this new method offers superior explainability of model prediction without sacrificing accuracy. This work demonstrates the feasibility and advantages of applying explainable machine learning techniques to the analysis of quantum dot measurements, paving the way for further advances in automated and transparent QD device tuning.
Authors: Hongjie Wu, Linchao He, Mingqin Zhang, Dongdong Chen, Kunming Luo, Mengting Luo, Ji-Zhe Zhou, Hu Chen, Jiancheng Lv
Abstract: Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources.
Authors: Ingo Steinwart
Abstract: In this paper we investigate the conditional distributions of two Banach space valued, jointly Gaussian random variables. We show that these conditional distributions are again Gaussian and that their means and covariances are determined by a general finite dimensional approximation scheme based upon a martingale approach. In particular, it turns out that the covariance operators occurring in this scheme converge with respect to the nuclear norm and that the conditional probabilities converge weakly. Moreover, we discuss in detail, how our approximation scheme can be implemented in several classes of important Banach spaces such as (reproducing kernel) Hilbert spaces and spaces of continuous functions. As an example, we then apply our general results to the case of Gaussian processes with continuous paths conditioned to partial but infinite observations of their paths. Here we show that conditioning on sufficiently rich, increasing sets of finitely many observations leads to consistent approximations, that is, both the mean and covariance functions converge uniformly and the conditional probabilities converge weakly. Moreover, we discuss how these results improve our understanding of the popular Gaussian processes for machine learning.
Authors: Tim Baumg\"artner, Yang Gao, Dana Alon, Donald Metzler
Abstract: Reinforcement Learning from Human Feedback (RLHF) is a popular method for aligning Language Models (LM) with human values and preferences. RLHF requires a large number of preference pairs as training data, which are often used in both the Supervised Fine-Tuning and Reward Model training and therefore publicly available datasets are commonly used. In this work, we study to what extent a malicious actor can manipulate the LMs generations by poisoning the preferences, i.e., injecting poisonous preference pairs into these datasets and the RLHF training process. We propose strategies to build poisonous preference pairs and test their performance by poisoning two widely used preference datasets. Our results show that preference poisoning is highly effective: injecting a small amount of poisonous data (1-5\% of the original dataset), we can effectively manipulate the LM to generate a target entity in a target sentiment (positive or negative). The findings from our experiments also shed light on strategies to defend against the preference poisoning attack.
Authors: Jiaxu Wang, Qiang Zhang, Jingkai Sun, Jiahang Cao, Gang Han, Wen Zhao, Weining Zhang, Yecheng Shao, Yijie Guo, Renjing Xu
Abstract: An excellent representation is crucial for reinforcement learning (RL) performance, especially in vision-based reinforcement learning tasks. The quality of the environment representation directly influences the achievement of the learning task. Previous vision-based RL typically uses explicit or implicit ways to represent environments, such as images, points, voxels, and neural radiance fields. However, these representations contain several drawbacks. They cannot either describe complex local geometries or generalize well to unseen scenes, or require precise foreground masks. Moreover, these implicit neural representations are akin to a ``black box", significantly hindering interpretability. 3D Gaussian Splatting (3DGS), with its explicit scene representation and differentiable rendering nature, is considered a revolutionary change for reconstruction and representation methods. In this paper, we propose a novel Generalizable Gaussian Splatting framework to be the representation of RL tasks, called GSRL. Through validation in the RoboMimic environment, our method achieves better results than other baselines in multiple tasks, improving the performance by 10%, 44%, and 15% compared with baselines on the hardest task. This work is the first attempt to leverage generalizable 3DGS as a representation for RL.
Authors: Jonas Ricker, Dennis Assenmacher, Thorsten Holz, Asja Fischer, Erwin Quiring
Abstract: Recent advances in the field of generative artificial intelligence (AI) have blurred the lines between authentic and machine-generated content, making it almost impossible for humans to distinguish between such media. One notable consequence is the use of AI-generated images for fake profiles on social media. While several types of disinformation campaigns and similar incidents have been reported in the past, a systematic analysis has been lacking. In this work, we conduct the first large-scale investigation of the prevalence of AI-generated profile pictures on Twitter. We tackle the challenges of a real-world measurement study by carefully integrating various data sources and designing a multi-stage detection pipeline. Our analysis of nearly 15 million Twitter profile pictures shows that 0.052% were artificially generated, confirming their notable presence on the platform. We comprehensively examine the characteristics of these accounts and their tweet content, and uncover patterns of coordinated inauthentic behavior. The results also reveal several motives, including spamming and political amplification campaigns. Our research reaffirms the need for effective detection and mitigation strategies to cope with the potential negative effects of generative AI in the future.
Authors: Qibin Liu, Chase Shimmin, Xiulong Liu, Eli Shlizerman, Shu Li, Shih-Chieh Hsu
Abstract: We introduce a novel machine learning method developed for the fast simulation of calorimeter detector response, adapting vector-quantized variational autoencoder (VQ-VAE). Our model adopts a two-stage generation strategy: initially compressing geometry-aware calorimeter data into a discrete latent space, followed by the application of a sequence model to learn and generate the latent tokens. Extensive experimentation on the Calo-challenge dataset underscores the efficiency of our approach, showcasing a remarkable improvement in the generation speed compared with conventional method by a factor of 2000. Remarkably, our model achieves the generation of calorimeter showers within milliseconds. Furthermore, comprehensive quantitative evaluations across various metrics are performed to validate physics performance of generation.
Authors: Lennart Heim, Leonie Koessler
Abstract: Regulators in the US and EU are using thresholds based on training compute--the number of computational operations used in training--to identify general-purpose artificial intelligence (GPAI) models that may pose risks of large-scale societal harm. We argue that training compute currently is the most suitable metric to identify GPAI models that deserve regulatory oversight and further scrutiny. Training compute correlates with model capabilities and risks, is quantifiable, can be measured early in the AI lifecycle, and can be verified by external actors, among other advantageous features. These features make compute thresholds considerably more suitable than other proposed metrics to serve as an initial filter to trigger additional regulatory requirements and scrutiny. However, training compute is an imperfect proxy for risk. As such, compute thresholds should not be used in isolation to determine appropriate mitigation measures. Instead, they should be used to detect potentially risky GPAI models that warrant regulatory oversight, such as through notification requirements, and further scrutiny, such as via model evaluations and risk assessments, the results of which may inform which mitigation measures are appropriate. In fact, this appears largely consistent with how compute thresholds are used today. As GPAI technology and market structures evolve, regulators should update compute thresholds and complement them with other metrics into regulatory review processes.
Authors: Li Jiang, Yusen Wu, Junwu Xiong, Jingqing Ruan, Yichuan Ding, Qingpei Guo, Zujie Wen, Jun Zhou, Xiaotie Deng
Abstract: Preference datasets are essential for incorporating human preferences into pre-trained language models, playing a key role in the success of Reinforcement Learning from Human Feedback. However, these datasets often demonstrate conflicting alignment objectives, leading to increased vulnerability to jailbreak attacks and challenges in adapting downstream tasks to prioritize specific alignment objectives without negatively impacting others. In this work, we introduce a novel statistical metric, Alignment Dimension Conflict, to quantify the degree of conflict within preference datasets. We then present \texttt{Hummer} and its fine-grained variant, \texttt{Hummer-F}, as innovative pairwise preference datasets with reduced-conflict alignment objectives. \texttt{Hummer} is built based on UltraFeedback and is enhanced by AI feedback from GPT-4, marking as the first preference dataset aimed at reducing the competition between alignment objectives. Furthermore, we develop reward models, HummerRM and HummerRM-F, which employ a hybrid sampling approach to balance diverse alignment objectives effectively. This sampling method positions HummerRM as an ideal model for domain-specific further fine-tuning and reducing vulnerabilities to attacks.
Authors: Xiang Li, Zebang Shen, Liang Zhang, Niao He
Abstract: Continuous-time approximation of Stochastic Gradient Descent (SGD) is a crucial tool to study its escaping behaviors from stationary points. However, existing stochastic differential equation (SDE) models fail to fully capture these behaviors, even for simple quadratic objectives. Built on a novel stochastic backward error analysis framework, we derive the Hessian-Aware Stochastic Modified Equation (HA-SME), an SDE that incorporates Hessian information of the objective function into both its drift and diffusion terms. Our analysis shows that HA-SME matches the order-best approximation error guarantee among existing SDE models in the literature, while achieving a significantly reduced dependence on the smoothness parameter of the objective. Further, for quadratic objectives, under mild conditions, HA-SME is proved to be the first SDE model that recovers exactly the SGD dynamics in the distributional sense. Consequently, when the local landscape near a stationary point can be approximated by quadratics, HA-SME is expected to accurately predict the local escaping behaviors of SGD.
Authors: Chao Wang, Jiaxuan Zhao, Lingling Li, Licheng Jiao, Fang Liu, Shuyuan Yang
Abstract: Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model's representation capabilities. However, manually determining the suitable Transformer architecture for a specific graph dataset or task requires extensive expert knowledge and laborious trials. This paper proposes an evolutionary graph Transformer architecture search framework (EGTAS) to automate the construction of strong graph Transformers. We build a comprehensive graph Transformer search space with the micro-level and macro-level designs. EGTAS evolves graph Transformer topologies at the macro level and graph-aware strategies at the micro level. Furthermore, a surrogate model based on generic architectural coding is proposed to directly predict the performance of graph Transformers, substantially reducing the evaluation cost of evolutionary search. We demonstrate the efficacy of EGTAS across a range of graph-level and node-level tasks, encompassing both small-scale and large-scale graph datasets. Experimental results and ablation studies show that EGTAS can construct high-performance architectures that rival state-of-the-art manual and automated baselines.
Authors: Karuna Bhaila, Minh-Hao Van, Xintao Wu
Abstract: The widespread popularity of Large Language Models (LLMs), partly due to their unique ability to perform in-context learning, has also brought to light the importance of ethical and safety considerations when deploying these pre-trained models. In this work, we focus on investigating machine unlearning for LLMs motivated by data protection regulations. In contrast to the growing literature on fine-tuning methods to achieve unlearning, we focus on a comparatively lightweight alternative called soft prompting to realize the unlearning of a subset of training data. With losses designed to enforce forgetting as well as utility preservation, our framework \textbf{S}oft \textbf{P}rompting for \textbf{U}n\textbf{l}earning (SPUL) learns prompt tokens that can be appended to an arbitrary query to induce unlearning of specific examples at inference time without updating LLM parameters. We conduct a rigorous evaluation of the proposed method and our results indicate that SPUL can significantly improve the trade-off between utility and forgetting in the context of text classification and question answering with LLMs. We further validate our method using multiple LLMs to highlight the scalability of our framework and provide detailed insights into the choice of hyperparameters and the influence of the size of unlearning data. Our implementation is available at \url{https://github.com/karuna-bhaila/llm_unlearning}.
Authors: Malte T\"olle, Lukas Burger, Halvar Kelm, Florian Andr\'e, Peter Bannas, Gerhard Diller, Norbert Frey, Philipp Garthe, Stefan Gro{\ss}, Anja Hennemuth, Lars Kaderali, Nina Kr\"uger, Andreas Leha, Simon Martin, Alexander Meyer, Eike Nagel, Stefan Orwat, Clemens Scherer, Moritz Seiffert, Jan Moritz Seliger, Stefan Simm, Tim Friede, Tim Seidler, Sandy Engelhardt
Abstract: Purpose: Federated training is often hindered by heterogeneous datasets due to divergent data storage options, inconsistent naming schemes, varied annotation procedures, and disparities in label quality. This is particularly evident in the emerging multi-modal learning paradigms, where dataset harmonization including a uniform data representation and filtering options are of paramount importance. Methods: DICOM structured reports enable the standardized linkage of arbitrary information beyond the imaging domain and can be used within Python deep learning pipelines with highdicom. Building on this, we developed an open platform for data integration and interactive filtering capabilities that simplifies the process of assembling multi-modal datasets. Results: In this study, we extend our prior work by showing its applicability to more and divergent data types, as well as streamlining datasets for federated training within an established consortium of eight university hospitals in Germany. We prove its concurrent filtering ability by creating harmonized multi-modal datasets across all locations for predicting the outcome after minimally invasive heart valve replacement. The data includes DICOM data (i.e. computed tomography images, electrocardiography scans) as well as annotations (i.e. calcification segmentations, pointsets and pacemaker dependency), and metadata (i.e. prosthesis and diagnoses). Conclusion: Structured reports bridge the traditional gap between imaging systems and information systems. Utilizing the inherent DICOM reference system arbitrary data types can be queried concurrently to create meaningful cohorts for clinical studies. The graphical interface as well as example structured report templates will be made publicly available.
Authors: Sunny Gupta, Amit Sethi
Abstract: Federated Learning (FL) offers a privacy-preserving approach to train models on decentralized data. Its potential in healthcare is significant, but challenges arise due to cross-client variations in medical image data, exacerbated by limited annotations. This paper introduces Cross-Client Variations Adaptive Federated Learning (CCVA-FL) to address these issues. CCVA-FL aims to minimize cross-client variations by transforming images into a common feature space. It involves expert annotation of a subset of images from each client, followed by the selection of a client with the least data complexity as the target. Synthetic medical images are then generated using Scalable Diffusion Models with Transformers (DiT) based on the target client's annotated images. These synthetic images, capturing diversity and representing the original data, are shared with other clients. Each client then translates its local images into the target image space using image-to-image translation. The translated images are subsequently used in a federated learning setting to develop a server model. Our results demonstrate that CCVA-FL outperforms Vanilla Federated Averaging by effectively addressing data distribution differences across clients without compromising privacy.
Authors: Ricardo Ferreira, Filipa Valdeira, Marta Guimar\~aes, Cl\'audia Soares
Abstract: With the increase in the number of active satellites and space debris in orbit, the problem of initial orbit determination (IOD) becomes increasingly important, demanding a high accuracy. Over the years, different approaches have been presented such as filtering methods (for example, Extended Kalman Filter), differential algebra or solving Lambert's problem. In this work, we consider a setting of three monostatic radars, where all available measurements are taken approximately at the same instant. This follows a similar setting as trilateration, a state-of-the-art approach, where each radar is able to obtain a single measurement of range and range-rate. Differently, and due to advances in Multiple-Input Multiple-Output (MIMO) radars, we assume that each location is able to obtain a larger set of range, angle and Doppler shift measurements. Thus, our method can be understood as an extension of trilateration leveraging more recent technology and incorporating additional data. We formulate the problem as a Maximum Likelihood Estimator (MLE), which for some number of observations is asymptotically unbiased and asymptotically efficient. Through numerical experiments, we demonstrate that our method attains the same accuracy as the trilateration method for the same number of measurements and offers an alternative and generalization, returning a more accurate estimation of the satellite's state vector, as the number of available measurements increases.
Authors: Hao Wang, Xiangyu Yang, Yichen Zhu
Abstract: This paper explores a specific type of nonconvex sparsity-promoting regularization problems, namely those involving $\ell_p$-norm regularization, in conjunction with a twice continuously differentiable loss function. We propose a novel second-order algorithm designed to effectively address this class of challenging nonconvex and nonsmooth problems, showcasing several innovative features: (i) The use of an alternating strategy to solve a reweighted $\ell_1$ regularized subproblem and the subspace approximate Newton step. (ii) The reweighted $\ell_1$ regularized subproblem relies on a convex approximation to the nonconvex regularization term, enabling a closed-form solution characterized by the soft-thresholding operator. This feature allows our method to be applied to various nonconvex regularization problems. (iii) Our algorithm ensures that the iterates maintain their sign values and that nonzero components are kept away from 0 for a sufficient number of iterations, eventually transitioning to a perturbed Newton method. (iv) We provide theoretical guarantees of global convergence, local superlinear convergence in the presence of the Kurdyka-\L ojasiewicz (KL) property, and local quadratic convergence when employing the exact Newton step in our algorithm. We also showcase the effectiveness of our approach through experiments on a diverse set of model prediction problems.
Authors: Xi Victoria Lin, Akshat Shrivastava, Liang Luo, Srinivasan Iyer, Mike Lewis, Gargi Gosh, Luke Zettlemoyer, Armen Aghajanyan
Abstract: We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into modality-specific groups. These groups exclusively process designated tokens while employing learned routing within each group to maintain semantically informed adaptivity. Our empirical results reveal substantial pre-training efficiency gains through this modality-specific parameter allocation. Under a 1-trillion-token training budget, the MoMa 1.4B model, featuring 4 text experts and 4 image experts, achieves impressive FLOPs savings: 3.7x overall, with 2.6x for text and 5.2x for image processing compared to a compute-equivalent dense baseline, measured by pre-training loss. This outperforms the standard expert-choice MoE with 8 mixed-modal experts, which achieves 3x overall FLOPs savings (3x for text, 2.8x for image). Combining MoMa with mixture-of-depths (MoD) further improves pre-training FLOPs savings to 4.2x overall (text: 3.4x, image: 5.3x), although this combination hurts performance in causal inference due to increased sensitivity to router accuracy. These results demonstrate MoMa's potential to significantly advance the efficiency of mixed-modal, early-fusion language model pre-training, paving the way for more resource-efficient and capable multimodal AI systems.
Authors: Xin Jiang, Kaiqiang Wang, Yinlong Wang, Fengchang Lv, Taiyang Peng, Shuai Yang, Xianteng Wu, Pengye Zhang, Shuo Yuan, Yifan Zeng
Abstract: In recommendation systems, the relevance and novelty of the final results are selected through a cascade system of Matching -> Ranking -> Strategy. The matching model serves as the starting point of the pipeline and determines the upper bound of the subsequent stages. Balancing the relevance and novelty of matching results is a crucial step in the design and optimization of recommendation systems, contributing significantly to improving recommendation quality. However, the typical matching algorithms have not simultaneously addressed the relevance and novelty perfectly. One main reason is that deep matching algorithms exhibit significant uncertainty when estimating items in the long tail (e.g., due to insufficient training samples) items.The uncertainty not only affects the training of the models but also influences the confidence in the index construction and beam search retrieval process of these models. This paper proposes the UICR (Uncertainty-based explore for Index Construction and Retrieval) algorithm, which introduces the concept of uncertainty modeling in the matching stage and achieves multi-task modeling of model uncertainty and index uncertainty. The final matching results are obtained by combining the relevance score and uncertainty score infered by the model. Experimental results demonstrate that the UICR improves novelty without sacrificing relevance on realworld industrial productive environments and multiple open-source datasets. Remarkably, online A/B test results of display advertising in Shopee demonstrates the effectiveness of the proposed algorithm.
Authors: Hyogun Lee, Soyeon Hong, Mujeen Sung, Jinwoo Choi
Abstract: In this work, we tackle the problem of long-form video-language grounding (VLG). Given a long-form video and a natural language query, a model should temporally localize the precise moment that answers the query. Humans can easily solve VLG tasks, even with arbitrarily long videos, by discarding irrelevant moments using extensive and robust knowledge gained from experience. Unlike humans, existing VLG methods are prone to fall into superficial cues learned from small-scale datasets, even when they are within irrelevant frames. To overcome this challenge, we propose EI-VLG, a VLG method that leverages richer textual information provided by a Multi-modal Large Language Model (MLLM) as a proxy for human experiences, helping to effectively exclude irrelevant frames. We validate the effectiveness of the proposed method via extensive experiments on a challenging EgoNLQ benchmark.
Authors: Danil Gusak, Gleb Mezentsev, Ivan Oseledets, Evgeny Frolov
Abstract: Scalability is a major challenge in modern recommender systems. In sequential recommendations, full Cross-Entropy (CE) loss achieves state-of-the-art recommendation quality but consumes excessive GPU memory with large item catalogs, limiting its practicality. Using a GPU-efficient locality-sensitive hashing-like algorithm for approximating large tensor of logits, this paper introduces a novel RECE (REduced Cross-Entropy) loss. RECE significantly reduces memory consumption while allowing one to enjoy the state-of-the-art performance of full CE loss. Experimental results on various datasets show that RECE cuts training peak memory usage by up to 12 times compared to existing methods while retaining or exceeding performance metrics of CE loss. The approach also opens up new possibilities for large-scale applications in other domains.