Machine Learning (cs.LG)

Abstract: In real-world datasets, noisy labels are pervasive. The challenge of learning with noisy labels (LNL) is to train a classifier that discerns the actual classes from given instances. For this, the model must identify features indicative of the authentic labels. While research indicates that genuine label information is embedded in the learned features of even inaccurately labeled data, it's often intertwined with noise, complicating its direct application. Addressing this, we introduce channel-wise contrastive learning (CWCL). This method distinguishes authentic label information from noise by undertaking contrastive learning across diverse channels. Unlike conventional instance-wise contrastive learning (IWCL), CWCL tends to yield more nuanced and resilient features aligned with the authentic labels. Our strategy is twofold: firstly, using CWCL to extract pertinent features to identify cleanly labeled samples, and secondly, progressively fine-tuning using these samples. Evaluations on several benchmark datasets validate our method's superiority over existing approaches.

Abstract: Problem Definition. Increasing costs of healthcare highlight the importance of effective disease prevention. However, decision models for allocating preventive care are lacking. Methodology/Results. In this paper, we develop a data-driven decision model for determining a cost-effective allocation of preventive treatments to patients at risk. Specifically, we combine counterfactual inference, machine learning, and optimization techniques to build a scalable decision model that can exploit high-dimensional medical data, such as the data found in modern electronic health records. Our decision model is evaluated based on electronic health records from 89,191 prediabetic patients. We compare the allocation of preventive treatments (metformin) prescribed by our data-driven decision model with that of current practice. We find that if our approach is applied to the U.S. population, it can yield annual savings of $1.1 billion. Finally, we analyze the cost-effectiveness under varying budget levels. Managerial Implications. Our work supports decision-making in health management, with the goal of achieving effective disease prevention at lower costs. Importantly, our decision model is generic and can thus be used for effective allocation of preventive care for other preventable diseases.

Abstract: Recently, graph neural networks (GNNs) have shown its unprecedented success in many graph-related tasks. However, GNNs face the label scarcity issue as other neural networks do. Thus, recent efforts try to pre-train GNNs on a large-scale unlabeled graph and adapt the knowledge from the unlabeled graph to the target downstream task. The adaptation is generally achieved by fine-tuning the pre-trained GNNs with a limited number of labeled data. Despite the importance of fine-tuning, current GNNs pre-training works often ignore designing a good fine-tuning strategy to better leverage transferred knowledge and improve the performance on downstream tasks. Only few works start to investigate a better fine-tuning strategy for pre-trained GNNs. But their designs either have strong assumptions or overlook the data-aware issue for various downstream datasets. Therefore, we aim to design a better fine-tuning strategy for pre-trained GNNs to improve the model performance in this paper. Given a pre-trained GNN, we propose to search to fine-tune pre-trained graph neural networks for graph-level tasks (S2PGNN), which adaptively design a suitable fine-tuning framework for the given labeled data on the downstream task. To ensure the improvement brought by searching fine-tuning strategy, we carefully summarize a proper search space of fine-tuning framework that is suitable for GNNs. The empirical studies show that S2PGNN can be implemented on the top of 10 famous pre-trained GNNs and consistently improve their performance. Besides, S2PGNN achieves better performance than existing fine-tuning strategies within and outside the GNN area. Our code is publicly available at \url{https://anonymous.4open.science/r/code_icde2024-A9CB/}.

Abstract: This paper introduces Bayesian Flow Networks (BFNs), a new class of generative model in which the parameters of a set of independent distributions are modified with Bayesian inference in the light of noisy data samples, then passed as input to a neural network that outputs a second, interdependent distribution. Starting from a simple prior and iteratively updating the two distributions yields a generative procedure similar to the reverse process of diffusion models; however it is conceptually simpler in that no forward process is required. Discrete and continuous-time loss functions are derived for continuous, discretised and discrete data, along with sample generation procedures. Notably, the network inputs for discrete data lie on the probability simplex, and are therefore natively differentiable, paving the way for gradient-based sample guidance and few-step generation in discrete domains such as language modelling. The loss function directly optimises data compression and places no restrictions on the network architecture. In our experiments BFNs achieve competitive log-likelihoods for image modelling on dynamically binarized MNIST and CIFAR-10, and outperform all known discrete diffusion models on the text8 character-level language modelling task.

Abstract: Label Distribution Learning (LDL) assigns soft labels, a.k.a. degrees, to a sample. In reality, it is always laborious to obtain complete degrees, giving birth to the Incomplete LDL (InLDL). However, InLDL often suffers from performance degeneration. To remedy it, existing methods need one or more explicit regularizations, leading to burdensome parameter tuning and extra computation. We argue that label distribution itself may provide useful prior, when used appropriately, the InLDL problem can be solved without any explicit regularization. In this paper, we offer a rational alternative to use such a prior. Our intuition is that large degrees are likely to get more concern, the small ones are easily overlooked, whereas the missing degrees are completely neglected in InLDL. To learn an accurate label distribution, it is crucial not to ignore the small observed degrees but to give them properly large weights, while gradually increasing the weights of the missing degrees. To this end, we first define a weighted empirical risk and derive upper bounds between the expected risk and the weighted empirical risk, which reveals in principle that weighting plays an implicit regularization role. Then, by using the prior of degrees, we design a weighted scheme and verify its effectiveness. To sum up, our model has four advantages, it is 1) model selection free, as no explicit regularization is imposed; 2) with closed form solution (sub-problem) and easy-to-implement (a few lines of codes); 3) with linear computational complexity in the number of samples, thus scalable to large datasets; 4) competitive with state-of-the-arts even without any explicit regularization.

Abstract: Deep learning methods are emerging as popular computational tools for solving forward and inverse problems in traffic flow. In this paper, we study a neural operator framework for learning solutions to nonlinear hyperbolic partial differential equations with applications in macroscopic traffic flow models. In this framework, an operator is trained to map heterogeneous and sparse traffic input data to the complete macroscopic traffic state in a supervised learning setting. We chose a physics-informed Fourier neural operator ($\pi$-FNO) as the operator, where an additional physics loss based on a discrete conservation law regularizes the problem during training to improve the shock predictions. We also propose to use training data generated from random piecewise constant input data to systematically capture the shock and rarefied solutions. From experiments using the LWR traffic flow model, we found superior accuracy in predicting the density dynamics of a ring-road network and urban signalized road. We also found that the operator can be trained using simple traffic density dynamics, e.g., consisting of $2-3$ vehicle queues and $1-2$ traffic signal cycles, and it can predict density dynamics for heterogeneous vehicle queue distributions and multiple traffic signal cycles $(\geq 2)$ with an acceptable error. The extrapolation error grew sub-linearly with input complexity for a proper choice of the model architecture and training data. Adding a physics regularizer aided in learning long-term traffic density dynamics, especially for problems with periodic boundary data.

Abstract: Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy violations, security breaches, and performance deterioration. To address these issues, machine unlearning has emerged as a critical technique to selectively remove specific training data points' influence on trained models. This paper provides a comprehensive taxonomy and analysis of machine unlearning research. We categorize existing research into exact unlearning that algorithmically removes data influence entirely and approximate unlearning that efficiently minimizes influence through limited parameter updates. By reviewing the state-of-the-art solutions, we critically discuss their advantages and limitations. Furthermore, we propose future directions to advance machine unlearning and establish it as an essential capability for trustworthy and adaptive machine learning. This paper provides researchers with a roadmap of open problems, encouraging impactful contributions to address real-world needs for selective data removal.

Abstract: Time-evolving data sets can often be arranged as a higher-order tensor with one of the modes being the time mode. While tensor factorizations have been successfully used to capture the underlying patterns in such higher-order data sets, the temporal aspect is often ignored, allowing for the reordering of time points. In recent studies, temporal regularizers are incorporated in the time mode to tackle this issue. Nevertheless, existing approaches still do not allow underlying patterns to change in time (e.g., spatial changes in the brain, contextual changes in topics). In this paper, we propose temporal PARAFAC2 (tPARAFAC2): a PARAFAC2-based tensor factorization method with temporal regularization to extract gradually evolving patterns from temporal data. Through extensive experiments on synthetic data, we demonstrate that tPARAFAC2 can capture the underlying evolving patterns accurately performing better than PARAFAC2 and coupled matrix factorization with temporal smoothness regularization.

Abstract: We present CounterfactualExplanations.jl: a package for generating Counterfactual Explanations (CE) and Algorithmic Recourse (AR) for black-box models in Julia. CE explain how inputs into a model need to change to yield specific model predictions. Explanations that involve realistic and actionable changes can be used to provide AR: a set of proposed actions for individuals to change an undesirable outcome for the better. In this article, we discuss the usefulness of CE for Explainable Artificial Intelligence and demonstrate the functionality of our package. The package is straightforward to use and designed with a focus on customization and extensibility. We envision it to one day be the go-to place for explaining arbitrary predictive models in Julia through a diverse suite of counterfactual generators.

Abstract: Neural support vector machines (NSVMs) allow for the incorporation of domain knowledge in the design of the model architecture. In this article we introduce a set of training algorithms for NSVMs that leverage the Pegasos algorithm and provide a proof of concept by solving a set of standard machine learning tasks.

Abstract: Structured pruning and quantization are promising approaches for reducing the inference time and memory footprint of neural networks. However, most existing methods require the original training dataset to fine-tune the model. This not only brings heavy resource consumption but also is not possible for applications with sensitive or proprietary data due to privacy and security concerns. Therefore, a few data-free methods are proposed to address this problem, but they perform data-free pruning and quantization separately, which does not explore the complementarity of pruning and quantization. In this paper, we propose a novel framework named Unified Data-Free Compression(UDFC), which performs pruning and quantization simultaneously without any data and fine-tuning process. Specifically, UDFC starts with the assumption that the partial information of a damaged(e.g., pruned or quantized) channel can be preserved by a linear combination of other channels, and then derives the reconstruction form from the assumption to restore the information loss due to compression. Finally, we formulate the reconstruction error between the original network and its compressed network, and theoretically deduce the closed-form solution. We evaluate the UDFC on the large-scale image classification task and obtain significant improvements over various network architectures and compression methods. For example, we achieve a 20.54% accuracy improvement on ImageNet dataset compared to SOTA method with 30% pruning ratio and 6-bit quantization on ResNet-34.

Abstract: A unifying $\alpha$-parametrized generator loss function is introduced for a dual-objective generative adversarial network (GAN), which uses a canonical (or classical) discriminator loss function such as the one in the original GAN (VanillaGAN) system. The generator loss function is based on a symmetric class probability estimation type function, $\mathcal{L}_\alpha$, and the resulting GAN system is termed $\mathcal{L}_\alpha$-GAN. Under an optimal discriminator, it is shown that the generator's optimization problem consists of minimizing a Jensen-$f_\alpha$-divergence, a natural generalization of the Jensen-Shannon divergence, where $f_\alpha$ is a convex function expressed in terms of the loss function $\mathcal{L}_\alpha$. It is also demonstrated that this $\mathcal{L}_\alpha$-GAN problem recovers as special cases a number of GAN problems in the literature, including VanillaGAN, Least Squares GAN (LSGAN), Least $k$th order GAN (L$k$GAN) and the recently introduced $(\alpha_D,\alpha_G)$-GAN with $\alpha_D=1$. Finally, experimental results are conducted on three datasets, MNIST, CIFAR-10, and Stacked MNIST to illustrate the performance of various examples of the $\mathcal{L}_\alpha$-GAN system.

Abstract: The Rash\=omon effect poses challenges for deriving reliable knowledge from machine learning models. This study examined the influence of sample size on explanations from models in a Rash\=omon set using SHAP. Experiments on 5 public datasets showed that explanations gradually converged as the sample size increased. Explanations from <128 samples exhibited high variability, limiting reliable knowledge extraction. However, agreement between models improved with more data, allowing for consensus. Bagging ensembles often had higher agreement. The results provide guidance on sufficient data to trust explanations. Variability at low samples suggests that conclusions may be unreliable without validation. Further work is needed with more model types, data domains, and explanation methods. Testing convergence in neural networks and with model-specific explanation methods would be impactful. The approaches explored here point towards principled techniques for eliciting knowledge from ambiguous models.

Abstract: lcensemble is a high-performing, scalable and user-friendly Python package for the general tasks of classification and regression. The package implements Local Cascade Ensemble (LCE), a machine learning method that further enhances the prediction performance of the current state-of-the-art methods Random Forest and XGBoost. LCE combines their strengths and adopts a complementary diversification approach to obtain a better generalizing predictor. The package is compatible with scikit-learn, therefore it can interact with scikit-learn pipelines and model selection tools. It is distributed under the Apache 2.0 license, and its source code is available at https://github.com/LocalCascadeEnsemble/LCE.

Abstract: Prompt-based pre-trained language models (PLMs) paradigm have succeeded substantially in few-shot natural language processing (NLP) tasks. However, prior discrete prompt optimization methods require expert knowledge to design the base prompt set and identify high-quality prompts, which is costly, inefficient, and subjective. Meanwhile, existing continuous prompt optimization methods improve the performance by learning the ideal prompts through the gradient information of PLMs, whose high computational cost, and low readability and generalizability are often concerning. To address the research gap, we propose a Dialogue-comprised Policy-gradient-based Discrete Prompt Optimization ($DP_2O$) method. We first design a multi-round dialogue alignment strategy for readability prompt set generation based on GPT-4. Furthermore, we propose an efficient prompt screening metric to identify high-quality prompts with linear complexity. Finally, we construct a reinforcement learning (RL) framework based on policy gradients to match the prompts to inputs optimally. By training a policy network with only 0.67% of the PLM parameter size on the tasks in the few-shot setting, $DP_2O$ outperforms the state-of-the-art (SOTA) method by 1.52% in accuracy on average on four open-source datasets. Moreover, subsequent experiments also demonstrate that $DP_2O$ has good universality, robustness, and generalization ability.

Abstract: Unmanned aerial vehicle (UAV)-enabled edge federated learning (FL) has sparked a rise in research interest as a result of the massive and heterogeneous data collected by UAVs, as well as the privacy concerns related to UAV data transmissions to edge servers. However, due to the redundancy of UAV collected data, e.g., imaging data, and non-rigorous FL participant selection, the convergence time of the FL learning process and bias of the FL model may increase. Consequently, we investigate in this paper the problem of selecting UAV participants for edge FL, aiming to improve the FL model's accuracy, under UAV constraints of energy consumption, communication quality, and local datasets' heterogeneity. We propose a novel UAV participant selection scheme, called data-efficient energy-aware participant selection strategy (DEEPS), which consists of selecting the best FL participant in each sub-region based on the structural similarity index measure (SSIM) average score of its local dataset and its power consumption profile. Through experiments, we demonstrate that the proposed selection scheme is superior to the benchmark random selection method, in terms of model accuracy, training time, and UAV energy consumption.