Machine Learning (cs.LG)

Abstract: Deep learning has been widely used in many fields, but the model training process usually consumes massive computational resources and time. Therefore, designing an efficient neural network training method with a provable convergence guarantee is a fundamental and important research question. In this paper, we present a static half-space report data structure that consists of a fully connected two-layer neural network for shifted ReLU activation to enable activated neuron identification in sublinear time via geometric search. We also prove that our algorithm can converge in $O(M^2/\epsilon^2)$ time with network size quadratic in the coefficient norm upper bound $M$ and error term $\epsilon$.

Abstract: Recently, the no-box adversarial attack, in which the attacker lacks access to the model's architecture, weights, and training data, become the most practical and challenging attack setup. However, there is an unawareness of the potential and flexibility inherent in the surrogate model selection process on no-box setting. Inspired by the burgeoning interest in utilizing foundational models to address downstream tasks, this paper adopts an innovative idea that 1) recasting adversarial attack as a downstream task. Specifically, image noise generation to meet the emerging trend and 2) introducing foundational models as surrogate models. Harnessing the concept of non-robust features, we elaborate on two guiding principles for surrogate model selection to explain why the foundational model is an optimal choice for this role. However, paradoxically, we observe that these foundational models underperform. Analyzing this unexpected behavior within the feature space, we attribute the lackluster performance of foundational models (e.g., CLIP) to their significant representational capacity and, conversely, their lack of discriminative prowess. To mitigate this issue, we propose the use of a margin-based loss strategy for the fine-tuning of foundational models on target images. The experimental results verify that our approach, which employs the basic Fast Gradient Sign Method (FGSM) attack algorithm, outstrips the performance of other, more convoluted algorithms. We conclude by advocating for the research community to consider surrogate models as crucial determinants in the effectiveness of adversarial attacks in no-box settings. The implications of our work bear relevance for improving the efficacy of such adversarial attacks and the overall robustness of AI systems.

Abstract: The performance of data fusion and tracking algorithms often depends on parameters that not only describe the sensor system, but can also be task-specific. While for the sensor system tuning these variables is time-consuming and mostly requires expert knowledge, intrinsic parameters of targets under track can even be completely unobservable until the system is deployed. With state-of-the-art sensor systems growing more and more complex, the number of parameters naturally increases, necessitating the automatic optimization of the model variables. In this paper, the parameters of an interacting multiple model (IMM) filter are optimized solely using measurements, thus without necessity for any ground-truth data. The resulting method is evaluated through an ablation study on simulated data, where the trained model manages to match the performance of a filter parametrized with ground-truth values.

Abstract: In this paper we consider online distributed learning problems. Online distributed learning refers to the process of training learning models on distributed data sources. In our setting a set of agents need to cooperatively train a learning model from streaming data. Differently from federated learning, the proposed approach does not rely on a central server but only on peer-to-peer communications among the agents. This approach is often used in scenarios where data cannot be moved to a centralized location due to privacy, security, or cost reasons. In order to overcome the absence of a central server, we propose a distributed algorithm that relies on a quantized, finite-time coordination protocol to aggregate the locally trained models. Furthermore, our algorithm allows for the use of stochastic gradients during local training. Stochastic gradients are computed using a randomly sampled subset of the local training data, which makes the proposed algorithm more efficient and scalable than traditional gradient descent. In our paper, we analyze the performance of the proposed algorithm in terms of the mean distance from the online solution. Finally, we present numerical results for a logistic regression task.

Abstract: Knowledge distillation (KD) has shown great potential for transferring knowledge from a complex teacher model to a simple student model in which the heavy learning task can be accomplished efficiently and without losing too much prediction accuracy. Recently, many attempts have been made by applying the KD mechanism to the graph representation learning models such as graph neural networks (GNNs) to accelerate the model's inference speed via student models. However, many existing KD-based GNNs utilize MLP as a universal approximator in the student model to imitate the teacher model's process without considering the graph knowledge from the teacher model. In this work, we provide a KD-based framework on multi-scaled GNNs, known as graph framelet, and prove that by adequately utilizing the graph knowledge in a multi-scaled manner provided by graph framelet decomposition, the student model is capable of adapting both homophilic and heterophilic graphs and has the potential of alleviating the over-squashing issue with a simple yet effectively graph surgery. Furthermore, we show how the graph knowledge supplied by the teacher is learned and digested by the student model via both algebra and geometry. Comprehensive experiments show that our proposed model can generate learning accuracy identical to or even surpass the teacher model while maintaining the high speed of inference.

Abstract: The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic factor on the sample complexity, leaving an open gap with the existing lower bound. We provide an improved uniform convergence bound that closes this gap.

Abstract: A wide variety of generative models for graphs have been proposed. They are used in drug discovery, road networks, neural architecture search, and program synthesis. Generating graphs has theoretical challenges, such as isomorphic representations -- evaluating how well a generative model performs is difficult. Which model to choose depending on the application domain? We extensively study kernel-based metrics on distributions of graph invariants and manifold-based and kernel-based metrics in graph embedding space. Manifold-based metrics outperform kernel-based metrics in embedding space. We use these metrics to compare GraphRNN and GRAN, two well-known generative models for graphs, and unveil the influence of node orderings. It shows the superiority of GRAN over GraphRNN - further, our proposed adaptation of GraphRNN with a depth-first search ordering is effective for small-sized graphs. A guideline on good practices regarding dataset selection and node feature initialization is provided. Our work is accompanied by open-source code and reproducible experiments.

Abstract: Time series forecasting has received wide interest from existing research due to its broad applications and inherent challenging. The research challenge lies in identifying effective patterns in historical series and applying them to future forecasting. Advanced models based on point-wise connected MLP and Transformer architectures have strong fitting power, but their secondary computational complexity limits practicality. Additionally, those structures inherently disrupt the temporal order, reducing the information utilization and making the forecasting process uninterpretable. To solve these problems, this paper proposes a forecasting model, MPR-Net. It first adaptively decomposes multi-scale historical series patterns using convolution operation, then constructs a pattern extension forecasting method based on the prior knowledge of pattern reproduction, and finally reconstructs future patterns into future series using deconvolution operation. By leveraging the temporal dependencies present in the time series, MPR-Net not only achieves linear time complexity, but also makes the forecasting process interpretable. By carrying out sufficient experiments on more than ten real data sets of both short and long term forecasting tasks, MPR-Net achieves the state of the art forecasting performance, as well as good generalization and robustness performance.

Abstract: The learning of Gaussian Mixture Models (also referred to simply as GMMs) plays an important role in machine learning. Known for their expressiveness and interpretability, Gaussian mixture models have a wide range of applications, from statistics, computer vision to distributional reinforcement learning. However, as of today, few known algorithms can fit or learn these models, some of which include Expectation-Maximization algorithms and Sliced Wasserstein Distance. Even fewer algorithms are compatible with gradient descent, the common learning process for neural networks. In this paper, we derive a closed formula of two GMMs in the univariate, one-dimensional case, then propose a distance function called Sliced Cram\'er 2-distance for learning general multivariate GMMs. Our approach has several advantages over many previous methods. First, it has a closed-form expression for the univariate case and is easy to compute and implement using common machine learning libraries (e.g., PyTorch and TensorFlow). Second, it is compatible with gradient descent, which enables us to integrate GMMs with neural networks seamlessly. Third, it can fit a GMM not only to a set of data points, but also to another GMM directly, without sampling from the target model. And fourth, it has some theoretical guarantees like global gradient boundedness and unbiased sampling gradient. These features are especially useful for distributional reinforcement learning and Deep Q Networks, where the goal is to learn a distribution over future rewards. We will also construct a Gaussian Mixture Distributional Deep Q Network as a toy example to demonstrate its effectiveness. Compared with previous models, this model is parameter efficient in terms of representing a distribution and possesses better interpretability.

Abstract: We initiate an empirical investigation into differentially private graph neural networks on population graphs from the medical domain by examining privacy-utility trade-offs at different privacy levels on both real-world and synthetic datasets and performing auditing through membership inference attacks. Our findings highlight the potential and the challenges of this specific DP application area. Moreover, we find evidence that the underlying graph structure constitutes a potential factor for larger performance gaps by showing a correlation between the degree of graph homophily and the accuracy of the trained model.

Abstract: In this study, we address the challenge of using energy-based models to produce high-quality, label-specific data in complex structured datasets, such as population genetics, RNA or protein sequences data. Traditional training methods encounter difficulties due to inefficient Markov chain Monte Carlo mixing, which affects the diversity of synthetic data and increases generation times. To address these issues, we use a novel training algorithm that exploits non-equilibrium effects. This approach, applied on the Restricted Boltzmann Machine, improves the model's ability to correctly classify samples and generate high-quality synthetic data in only a few sampling steps. The effectiveness of this method is demonstrated by its successful application to four different types of data: handwritten digits, mutations of human genomes classified by continental origin, functionally characterized sequences of an enzyme protein family, and homologous RNA sequences from specific taxonomies.

Abstract: The field of Tiny Machine Learning (TinyML) has made substantial advancements in democratizing machine learning on low-footprint devices, such as microcontrollers. The prevalence of these miniature devices raises the question of whether aggregating their knowledge can benefit TinyML applications. Federated meta-learning is a promising answer to this question, as it addresses the scarcity of labeled data and heterogeneous data distribution across devices in the real world. However, deploying TinyML hardware faces unique resource constraints, making existing methods impractical due to energy, privacy, and communication limitations. We introduce TinyMetaFed, a model-agnostic meta-learning framework suitable for TinyML. TinyMetaFed facilitates collaborative training of a neural network initialization that can be quickly fine-tuned on new devices. It offers communication savings and privacy protection through partial local reconstruction and Top-P% selective communication, computational efficiency via online learning, and robustness to client heterogeneity through few-shot learning. The evaluations on three TinyML use cases demonstrate that TinyMetaFed can significantly reduce energy consumption and communication overhead, accelerate convergence, and stabilize the training process.

Abstract: Domain generalization (DG) is about learning models that generalize well to new domains that are related to, but different from, the training domain(s). It is a fundamental problem in machine learning and has attracted much attention in recent years. A large number of approaches have been proposed. Different approaches are motivated from different perspectives, making it difficult to gain an overall understanding of the area. In this paper, we propose a causal framework for domain generalization and present an understanding of common DG approaches in the framework. Our work sheds new lights on the following questions: (1) What are the key ideas behind each DG method? (2) Why is it expected to improve generalization to new domains theoretically? (3) How are different DG methods related to each other and what are relative advantages and limitations? By providing a unified perspective on DG, we hope to help researchers better understand the underlying principles and develop more effective approaches for this critical problem in machine learning.

Abstract: Local authorities in England, such as Leicestershire County Council (LCC), provide Early Help services that can be offered at any point in a young person's life when they experience difficulties that cannot be supported by universal services alone, such as schools. This paper investigates the utilisation of machine learning (ML) to assist experts in identifying families that may need to be referred for Early Help assessment and support. LCC provided an anonymised dataset comprising 14360 records of young people under the age of 18. The dataset was pre-processed, machine learning models were build, and experiments were conducted to validate and test the performance of the models. Bias mitigation techniques were applied to improve the fairness of these models. During testing, while the models demonstrated the capability to identify young people requiring intervention or early help, they also produced a significant number of false positives, especially when constructed with imbalanced data, incorrectly identifying individuals who most likely did not need an Early Help referral. This paper empirically explores the suitability of data-driven ML models for identifying young people who may require Early Help services and discusses their appropriateness and limitations for this task.

Abstract: The problem of continual learning in the domain of reinforcement learning, often called non-stationary reinforcement learning, has been identified as an important challenge to the application of reinforcement learning. We prove a worst-case complexity result, which we believe captures this challenge: Modifying the probabilities or the reward of a single state-action pair in a reinforcement learning problem requires an amount of time almost as large as the number of states in order to keep the value function up to date, unless the strong exponential time hypothesis (SETH) is false; SETH is a widely accepted strengthening of the P $\neq$ NP conjecture. Recall that the number of states in current applications of reinforcement learning is typically astronomical. In contrast, we show that just $\textit{adding}$ a new state-action pair is considerably easier to implement.

Abstract: Delays and asynchrony are inevitable in large-scale machine-learning problems where communication plays a key role. As such, several works have extensively analyzed stochastic optimization with delayed gradients. However, as far as we are aware, no analogous theory is available for min-max optimization, a topic that has gained recent popularity due to applications in adversarial robustness, game theory, and reinforcement learning. Motivated by this gap, we examine the performance of standard min-max optimization algorithms with delayed gradient updates. First, we show (empirically) that even small delays can cause prominent algorithms like Extra-gradient (\texttt{EG}) to diverge on simple instances for which \texttt{EG} guarantees convergence in the absence of delays. Our empirical study thus suggests the need for a careful analysis of delayed versions of min-max optimization algorithms. Accordingly, under suitable technical assumptions, we prove that Gradient Descent-Ascent (\texttt{GDA}) and \texttt{EG} with delayed updates continue to guarantee convergence to saddle points for convex-concave and strongly convex-strongly concave settings. Our complexity bounds reveal, in a transparent manner, the slow-down in convergence caused by delays.

Abstract: Feature learning, i.e. extracting meaningful representations of data, is quintessential to the practical success of neural networks trained with gradient descent, yet it is notoriously difficult to explain how and why it occurs. Recent theoretical studies have shown that shallow neural networks optimized on a single task with gradient-based methods can learn meaningful features, extending our understanding beyond the neural tangent kernel or random feature regime in which negligible feature learning occurs. But in practice, neural networks are increasingly often trained on {\em many} tasks simultaneously with differing loss functions, and these prior analyses do not generalize to such settings. In the multi-task learning setting, a variety of studies have shown effective feature learning by simple linear models. However, multi-task learning via {\em nonlinear} models, arguably the most common learning paradigm in practice, remains largely mysterious. In this work, we present the first results proving feature learning occurs in a multi-task setting with a nonlinear model. We show that when the tasks are binary classification problems with labels depending on only $r$ directions within the ambient $d\gg r$-dimensional input space, executing a simple gradient-based multitask learning algorithm on a two-layer ReLU neural network learns the ground-truth $r$ directions. In particular, any downstream task on the $r$ ground-truth coordinates can be solved by learning a linear classifier with sample and neuron complexity independent of the ambient dimension $d$, while a random feature model requires exponential complexity in $d$ for such a guarantee.

Abstract: Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution estimates such as pixel saliency. However, defining the concepts for the interpretability analysis biases the explanations by the user's expectations on the concepts. To address this, we propose a novel post-hoc unsupervised method that automatically uncovers the concepts learned by deep models during training. By decomposing the latent space of a layer in singular vectors and refining them by unsupervised clustering, we uncover concept vectors aligned with directions of high variance that are relevant to the model prediction, and that point to semantically distinct concepts. Our extensive experiments reveal that the majority of our concepts are readily understandable to humans, exhibit coherency, and bear relevance to the task at hand. Moreover, we showcase the practical utility of our method in dataset exploration, where our concept vectors successfully identify outlier training samples affected by various confounding factors. This novel exploration technique has remarkable versatility to data types and model architectures and it will facilitate the identification of biases and the discovery of sources of error within training data.