Search

Gradient inversion attacks (GIAs) have posed significant challenges to the emerging paradigm of distributed learning, which aims to reconstruct the private training data of clients (participating parties in distributed training) through the shared parameters. For counteracting GIAs, a large number of privacy-preserving methods for distributed learning scenario have emerged. However, these methods have significant limitations, either compromising the usability of global model or consuming substantial additional computational resources. Furthermore, despite the extensive efforts dedicated to defense methods, the underlying causes of data leakage in distributed learning still have not been thoroughly investigated. Therefore, this paper tries to reveal the potential reasons behind the successful implementation of existing GIAs, explore variations in the robustness of models against GIAs during the training process, and investigate the impact of different model structures on attack performance. After these explorations and analyses, this paper propose a plug-and-play GIAs defense method, which augments the training data by a designed vicinal distribution. Sufficient empirical experiments demonstrate that this easy-to-implement method can ensure the basic level of privacy without compromising the usability of global model.

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources. To enable the deployment of modern models on resource-constrained environments and to accelerate inference time, researchers have increasingly explored pruning techniques as a popular research direction in neural network compression. More than three thousand pruning papers have been published from 2020 to 2024. However, there is a dearth of up-to-date comprehensive review papers on pruning. To address this issue, in this survey, we provide a comprehensive review of existing research works on deep neural network pruning in a taxonomy of 1) universal/specific speedup, 2) when to prune, 3) how to prune, and 4) fusion of pruning and other compression techniques. We then provide a thorough comparative analysis of eight pairs of contrast settings for pruning (e.g., unstructured/structured, one-shot/iterative, data-free/data-driven, initialized/pre-trained weights, etc.) and explore several emerging topics, including pruning for large language models, vision transformers, diffusion models, and large multimodal models, post-training pruning, and different levels of supervision for pruning to shed light on the commonalities and differences of existing methods and lay the foundation for further method development. Finally, we provide some valuable recommendations on selecting pruning methods and prospect several promising research directions for neural network pruning. To facilitate future research on deep neural network pruning, we summarize broad pruning applications (e.g., adversarial robustness, natural language understanding, etc.) and build a curated collection of datasets, networks, and evaluations on different applications. We maintain a repository on https://github.com/hrcheng1066/awesome-pruning that serves as a comprehensive resource for neural network pruning papers and corresponding open-source codes. We will keep updating this repository to include the latest advancements in the field.

The key challenges in cloud computing encompass dynamic resource scaling, load balancing, and power consumption. Accurate workload prediction is identified as a crucial strategy to address these challenges. Despite numerous methods proposed to tackle this issue, existing approaches fall short of capturing the high-variance nature of volatile and dynamic cloud workloads. Consequently, this paper introduces a novel model aimed at addressing this limitation. This paper presents a novel Multiple Controlled Toffoli-driven Adaptive Quantum Neural Network (MCT-AQNN) model to establish an empirical solution to complex, elastic as well as challenging workload prediction problems by optimizing the exploration, adaption, and exploitation proficiencies through quantum learning. The computational adaptability of quantum computing is ingrained with machine learning algorithms to derive more precise correlations from dynamic and complex workloads. The furnished input data point and hatched neural weights are refitted in the form of qubits while the controlling effects of Multiple Controlled Toffoli (MCT) gates are operated at the hidden and output layers of Quantum Neural Network (QNN) for enhancing learning capabilities. Complimentarily, a Uniformly Adaptive Quantum Machine Learning (UAQL) algorithm has evolved to functionally and effectually train the QNN. The extensive experiments are conducted and the comparisons are performed with state-of-the-art methods using four real-world benchmark datasets. Experimental results evince that MCT-AQNN has up to 32%–96% higher accuracy than the existing approaches.

Mixed-precision Deep Neural Networks (DNNs) provide an efficient solution for hardware deployment, especially under resource constraints, while maintaining model accuracy. Identifying the ideal bit precision for each layer, however, remains a challenge given the vast array of models, datasets, and quantization schemes, leading to an expansive search space. Recent literature has addressed this challenge, resulting in several promising frameworks. This paper offers a comprehensive overview of the standard quantization classifications prevalent in existing studies. A detailed survey of current mixed-precision frameworks is provided, with an in-depth comparative analysis highlighting their respective merits and limitations. The paper concludes with insights into potential avenues for future research in this domain.

This paper provides developments in statistical shape analysis of shape graphs, and demonstrates them using such complex objects as Retinal Blood Vessel (RBV) networks and neurons. The shape graphs are represented by sets of nodes and edges (articulated curves) connecting some nodes. The goals are to utilize nodes (locations, connectivity) and edges (edge weights and shapes) to: (1) characterize shapes, (2) quantify shape differences, and (3) model statistical variability. We develop a mathematical representation, elastic Riemannian metrics, and associated tools for shape graphs. Specifically, we derive tools for shape graph registration, geodesics, statistical summaries, shape modeling, and shape synthesis. Geodesics are convenient for visualizing optimal deformations, and PCA helps in dimension reduction and statistical modeling. One key challenge lies in comparing shape graphs with vastly different complexities (in number of nodes and edges). This paper introduces a novel multi-scale representation to handle this challenge. Using the notions of (1) “effective resistance” to cluster nodes and (2) elastic shape averaging of edge curves, it reduces graph complexity while retaining overall structures. This allows shape comparisons by bringing graphs to similar complexities. We demonstrate these ideas on 2D RBV networks from the STARE and DRIVE databases and 3D neurons from the NeuroMorpho database.

In recent years, vision-centric Bird’s Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing an intuitive representation of the world and being conducive to data fusion. The rapid advancements in deep learning have led to the proposal of numerous methods for addressing vision-centric BEV perception challenges. However, there has been no recent survey encompassing this novel and burgeoning research field. To catalyze future research, this paper presents a comprehensive survey of the latest developments in vision-centric BEV perception and its extensions. It compiles and organizes up-to-date knowledge, offering a systematic review and summary of prevalent algorithms. Additionally, the paper provides in-depth analyses and comparative results on various BEV perception tasks, facilitating the evaluation of future works and sparking new research directions. Furthermore, the paper discusses and shares valuable empirical implementation details to aid in the advancement of related algorithms.

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to introduce a set of multiple representations for each user in the system where users’ preference toward an item is aggregated by taking the minimum item-user distance among their embedding set. Specifically, we instantiate two effective assignment strategies to explore a proper quantity of vectors for each user. Meanwhile, a Diversity Control Regularization Scheme (DCRS) is developed to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could induce a smaller generalization error than traditional CML. Furthermore, we notice that CML-based approaches usually require negative sampling to reduce the heavy computational burden caused by the pairwise objective therein. In this paper, we reveal the fundamental limitation of the widely adopted hard-aware sampling from the One-Way Partial AUC (OPAUC) perspective and then develop an effective sampling alternative for the CML-based paradigm. Finally, comprehensive experiments over a range of benchmark datasets speak to the efficacy of DPCML.

Human gaze provides valuable information on human focus and intentions, making it a crucial area of research. Recently, deep learning has revolutionized appearance-based gaze estimation. However, due to the unique features of gaze estimation research, such as the unfair comparison between 2D gaze positions and 3D gaze vectors and the different pre-processing and post-processing methods, there is a lack of a definitive guideline for developing deep learning-based gaze estimation algorithms. In this paper, we present a systematic review of the appearance-based gaze estimation methods using deep learning. First, we survey the existing gaze estimation algorithms along the typical gaze estimation pipeline: deep feature extraction, deep learning model design, personal calibration and platforms. Second, to fairly compare the performance of different approaches, we summarize the data pre-processing and post-processing methods, including face/eye detection, data rectification, 2D/3D gaze conversion and gaze origin conversion. Finally, we set up a comprehensive benchmark for deep learning-based gaze estimation. We characterize all the public datasets and provide the source code of typical gaze estimation algorithms. This paper serves not only as a reference to develop deep learning-based gaze estimation methods, but also a guideline for future gaze estimation research.

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism, outperforming earlier convolutional neural networks. However, ViT deployment and performance have grown steadily with their size, number of trainable parameters, and operations. Furthermore, self-attention's computational and memory cost quadratically increases with the image resolution. Generally speaking, it is challenging to employ these architectures in real-world applications due to many hardware and environmental restrictions, such as processing and computational capabilities. Therefore, this survey investigates the most efficient methodologies to ensure sub-optimal estimation performances. More in detail, four efficient categories will be analyzed: compact architecture, pruning, knowledge distillation, and quantization strategies. Moreover, a new metric called Efficient Error Rate has been introduced in order to normalize and compare models’ features that affect hardware devices at inference time, such as the number of parameters, bits, FLOPs, and model size. Summarizing, this paper first mathematically defines the strategies used to make Vision Transformer efficient, describes and discusses state-of-the-art methodologies, and analyzes their performances over different application scenarios. Toward the end of this paper, we also discuss open challenges and promising research directions.