As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques that can be used to confirm the ownership of a particular model. Unfortunately, these methods usually produce watermarks susceptible to model stealing attacks. In our research, we introduce a novel trigger set-based watermarking approach that demonstrates resilience against functionality stealing attacks, particularly those involving extraction and distillation. Our approach does not require additional model training and can be applied to any model architecture. The key idea of our method is to compute the trigger set, which is transferable between the source model and the set of proxy models with a high probability. In our experimental study, we show that if the probability of the set being transferable is reasonably high, it can be effectively used for ownership verification of the stolen model. We evaluate our method on multiple benchmarks and show that our approach outperforms current state-of-the-art watermarking techniques in all considered experimental setups.
论文检索
输入标题、作者或关键词，从 1,048 篇学术成果中精准定位
Alzheimer's disease (AD) leads to abnormalities in various biomarkers (i.e., amyloid-β and tau proteins), which makes PET imaging (which can detect these biomarkers) essential in AD diagnosis. However, the high radiation risk of PET imaging limits its scanning number within a short period, presenting challenges to the joint multi-biomarker diagnosis of AD. In this paper, we propose a novel unified model to simultaneously synthesize multi-modal PET images from MRI, to achieve low-cost and time-efficient joint multi-biomarker diagnosis of AD. Specifically, we incorporate residual learning into the diffusion model to emphasize inter-domain differences between PET and MRI, thereby forcing each modality to maximally reconstruct its modality-specific details. Furthermore, we leverage prior information, such as age and gender, to guide the diffusion model in synthesizing PET images with semantic consistency, enhancing their diagnostic value. Additionally, we develop an intra-domain difference loss to ensure that the intra-domain differences among synthesized PET images closely match those among real PET images, promoting more accurate synthesis, especially at the modality-specific information. Extensive experiments conducted on the ADNI dataset demonstrate that our method achieves superior performance both quantitatively and qualitatively compared to the state-of-the-art methods. All codes for this study have been uploaded to GitHub (https://github.com/Ouzaixin/ResDM).
FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization
PDF ↗Federated Learning faces significant challenges in statistical and system heterogeneity, along with high energy consumption, necessitating efficient client selection strategies. Traditional approaches, including heuristic and learning-based methods, fall short of addressing these complexities holistically. In response, we propose FedGCS, a novel generative client selection framework that innovatively recasts the client selection process as a generative task. Drawing inspiration from the methodologies used in large language models, FedGCS efficiently encodes abundant decision-making knowledge within a continuous representation space, enabling efficient gradient-based optimization to search for optimal client selection that will be finally output via generation. The framework comprises four steps: (1) automatic collection of diverse “selection-score” pair data using classical client selection methods; (2) training an encoder-evaluator-decoder framework on this data to construct a continuous representation space; (3) employing gradient-based optimization in this space for optimal client selection; (4) generating the final optimal client selection via using beam search for the well-trained decoder. FedGCS outperforms traditional methods by being more comprehensive, generalizable, and efficient, simultaneously optimizing for model performance, latency, and energy consumption. The effectiveness of FedGCS is proven through extensive experimental analyses.
The estimation of probability density functions is a fundamental problem in science and engineering. However, common methods such as kernel density estimation (KDE) have been demonstrated to lack robustness, while more complex methods have not been evaluated in multi-modal estimation problems. In this paper, we present ROME (RObust Multi-modal Estimator), a non-parametric approach for density estimation which addresses the challenge of estimating multi-modal, non-normal, and highly correlated distributions. ROME utilizes clustering to segment a multi-modal set of samples into multiple uni-modal ones and then combines simple KDE estimates obtained for individual clusters in a single multi-modal estimate. We compared our approach to state-of-the-art methods for density estimation as well as ablations of ROME, showing that it not only outperforms established methods but is also more robust to a variety of distributions. Our results demonstrate that ROME can overcome the issues of over-fitting and over-smoothing exhibited by other estimators.
Multi-label metric learning serve as an effective strategy to facilitate multi-label classification, aiming to learn better similarity metrics from multi-label examples. Existing multi-label metric learning approaches learn consistent metrics across all multi-label instances in the label space. However, such consistent metric learning approaches are suboptimal as they neglect the nonlinear distribution characteristics of multi-label instances. In this paper, we present LSMM, a label-specific multi-metric learning framework for multi-label classification, where nonlinear distribution characteristics of multi-label examples are considered by learning label-specific multiple local metrics for different instances on the shoulder of a global one. Specifically, multi-label instances within each label space can be divided into several disjoint partitions through either semantic-based or cluster-based partition strategies, in each of which a local metric is trained to separate the instances locally. Besides, a global metric is introduced to implicitly exploit high-order label correlations across all labels. The combination of the global metric and label-specific local metrics is utilized to measure the semantic similarities between multi-label instances in each label space, under which similar intra-class instances are pushed closer and inter-class instances are pulled apart. Comprehensive experiments on benchmark multi-label data sets validate the superiority of LSMM in learning effective similarity metrics for multi-label classification.
We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty about its performance on the other. This intuition is captured by our information-theoretic criterion which uses a diverse agent population as an approximation for the space of agents to measure similarity between tasks in sequential decision-making settings. In addition to qualitative assessment, we empirically demonstrate the effectiveness of our techniques based on task embeddings by quantitative comparisons against strong baselines on two application scenarios: predicting an agent's performance on a new task by observing its performance on a small quiz of tasks, and selecting tasks with desired characteristics from a given set of options.
Self-supervised learning (SSL) aims to learn the intrinsic features of data without labels. Despite the diverse SSL architectures, the projection head always plays an important role in improving downstream task performance. In this study, we systematically investigate the role of the projection head in SSL. We find that the projection head targets the uniformity aspect, which maps samples into uniform distribution and enables the encoder to focus on extracting semantic features. Drawing on this insight, we propose a Representation Evaluation Design (RED) in SSL models in which a shortcut connection between the representation and the projection vectors is built. Our extensive experiments with different architectures (including SimCLR, MoCo-V2, and SimSiam) on various datasets demonstrate that the RED-SSL consistently outperforms their baseline counterparts in downstream tasks. Furthermore, the RED-SSL learned representations exhibit superior robustness to previously unseen augmentations and out-of-distribution data.
In Multi-View Multi-Label Learning, each instance is described by several heterogeneous features and associated with multiple valid labels simultaneously. Existing methods mainly focus on leveraging feature-level view fusion to capture a common representation for multi-label classifier induction. In this paper, we take a new perspective and propose a new semantic-level fusion model named Common-Individual Semantic Fusion Multi-View Multi-Label Learning Method (CISF). Different from previous feature-level fusion model, our proposed method directly focuses on semantic-level view fusion and simultaneously take both the common semantic across different views and the individual semantic of each specific view into consideration. Specifically, we first assume each view involves some common semantic labels while owns a few exclusive semantic labels. Then, the common and exclusive semantic labels are separately forced to be consensus and diverse to excavate the consistences and complementarities among different views. Afterwards, we introduce the low-rank and sparse constraint to highlight the label co-occurrence relationship of common semantics and the view-specific expression of individual semantics. We provide theoretical guarantee for the strict convexity of our method by properly setting parameters. Extensive experiments on various data sets have verified the superiority of our method.
Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inharmonic graphs with harmonic graphs which close to the source domain for subgraph extraction. In particular, to overcome label scarcity, we employ the spectral seriation algorithm to infer the robust pairwise rankings, which can guide semantic learning using a similarity learning objective. To depict distribution shifts, we utilize spectral clustering and the silhouette coefficient to detect harmonic graphs, which the source model can easily classify. To reduce potential domain discrepancy, we extract domain-invariant subgraphs from inharmonic graphs by an adversarial edge sampling process, which guides the invariant learning of GNNs. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed RNA.
Previous deep multi-view clustering methods usually design un-shared encoders to explore the cluster information among multi-view data, but they are difficult to customize the encoders for individual views and easily increase information loss. To address these issues, we propose a simple yet effective contrastive multi-view clustering framework. Specifically, different from using feature-level fusion in previous methods, we first propose a data-level fusion method to fuse multi-view information, which produces a fused data to replace all views and thus avoids customizing networks for different views. Then, we simulate the data noise and unavailability in multiple views to design two kinds of data augmentation for the fused data, making a shared encoder with simple contrastive learning to learn robust features and achieve the interaction across views. As a result, our method is a general framework and we base on it to conduct feature clustering and end-to-end clustering. Extensive experiments demonstrate that our method can explore the discriminative information in multi-view data and achieve superior clustering performance.
The Orthogonality of Weight Vectors: The Key Characteristics of Normalization and Residual Connections
PDF ↗Normalization and residual connections find extensive application within the intricate architecture of deep neural networks, contributing significantly to their heightened performance. Nevertheless, the precise factors responsible for this elevated performance have remained elusive. Our theoretical investigations have unveiled a noteworthy revelation: the utilization of normalization and residual connections results in an enhancement of the orthogonality within the weight vectors of deep neural networks. This, in turn, induces the Gram matrix of neural network weights to exhibit a pronounced tendency towards strict diagonal dominance, thereby amplifying the neural network's capacity for feature learning. Meanwhile, we have designed the parameters independence index (PII) to precisely characterize the orthogonality of parameter vectors. In tandem with our theoretical findings, we undertook empirical validations through experiments conducted on prevalent network models, including fully connected networks (FNNs), convolutional neural networks (CNNs), Transformers, pre-trained language models(PLMs) and large language models (LLMs) composed of Transformers. Finally, we have found that a fine-tuning technique (LoRA) preserves the orthogonality of parameter vectors, a revelation that carries importance within the framework of fine-tuning techniques for LLMs.
Recently, various deep denoising methods have been proposed to solve the insufficient feature problem in image denoising. These methods can be mainly classified into two categories: (1) Injecting learnable tensors into denoising backbone to supplement feature, which is effective to some extent but may cause serious over-fitting. (2) Using diverse natural images from large image datasets to synthesize noisy images and pre-train denoising models, which can bring model generalization but require large model size and expensive training costs. To address these issues, this paper proposes Implicit Prompt Learning for Image Denoising (IPLID) method to flexibly generate adaptive prompts without meticulously designing them. Specifically, we first introduce an efficient Linear Prompt (LP) block with ultra-few parameters to produce dynamic prompts for both different stages and samples in denoising procedure. We further propose an efficient Compact Feature Fusion (CFF) block to process previous multi-level prompted denoising feature to reconstruct the denoising images. Finally, to further efficiently and effectively produce satisfactory prompt and denoising performance, a Gradient Accumulation (GA) learning scheme is proposed. Experiments on multiple benchmarks showed that the proposed IPLID achieves competitive results with only 1 percent of pre-trained backbone parameters, outperforming classical denoising methods in both efficiency and quality of restored images.
Alleviating Imbalanced Pseudo-label Distribution: Self-Supervised Multi-Source Domain Adaptation with Label-specific Confidence
PDF ↗The existing self-supervised Multi-Source Domain Adaptation (MSDA) methods often suffer an imbalanced characteristic among the distribution of pseudo-labels. Such imbalanced characteristic results in many labels with too many or too few pseudo-labeled samples on the target domain, referred to as easy-to-learn label and hard-to-learn label, respectively. Both of these labels hurt the generalization performance on the target domain. To alleviate this problem, in this paper we propose a novel multi-source domain adaptation method, namely Self-Supervised multi-Source Domain Adaptation with Label-specific Confidence (S3DA-LC). Specifically, we estimate the label-specific confidences, i.e., the learning difficulties of labels, and adopt them to generate the pseudo-labels for target samples, enabling to simultaneously constrain and enrich the pseudo supervised signals for easy-to-learn and hard-to-learn labels. We evaluate S3DA-LC on several benchmark datasets, indicating its superior performance compared with the existing MSDA baselines.
LEAP: Optimization Hierarchical Federated Learning on Non-IID Data with Coalition Formation Game
PDF ↗Although Hierarchical Federated Learning (HFL) utilizes edge servers (ESs) to alleviate communication burdens, its model performance will be degraded by non-IID data and limited communication resources. Current works often assume that data is uniformly distributed, which however contradicts the heterogeneity of IoT. Solutions involving additional model training to check the data distribution inevitably increase computational costs and the risk of privacy leakage. The challenges in solving these issues are how to reduce the impact of non-IID data without involving raw data, and how to rationalize the communication resource allocation for addressing straggler problem. To tackle these challenges, we propose a novel optimization method based on coaLition formation gamE and grAdient Projection, called LEAP. Specifically, we combine edge data distribution with coalition formation game innovatively to adjust the correlations between clients and ESs dynamically, ensuring optimal correlations. We further capture the client heterogeneity to achieve the rational bandwidth allocation from coalition perception and determine the optimal transmission power within specified delay constraints at the client level. Experimental results on four real datasets show that LEAP is able to achieve 20.62% improvement in model accuracy compared to the state-of-the-art baselines. Moreover, LEAP effectively reduces transmission energy consumption by at least about 2.24 times.
Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, width, and components) in contributing to CL. This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL. This work considers architecture design at the network scaling level, i.e., width and depth, and also at the network components, i.e., skip connections, global pooling layers, and down-sampling. In both cases, we first derive insights through systematically exploring how architectural designs affect CL. Then, grounded in these insights, we craft a specialized search space for CL and further propose a simple yet effective ArchCraft method to steer a CL-friendly architecture, namely, this method recrafts AlexNet/ResNet into AlexAC/ResAC. Experimental validation across various CL settings and scenarios demonstrates that improved architectures are parameter-efficient, achieving state-of-the-art performance of CL while being 86%, 61%, and 97% more compact in terms of parameters than the naive CL architecture in Task IL and Class IL. Code is available at https://github.com/byyx666/ArchCraft.
Multi-view clustering (MVC) is a long-standing topic in machine learning and data mining community, focusing on investigating and utilizing the relationships among views for final consistent data cluster structure discovery. Generally, weighted MVC is one of the popular methods working by learning and applying the view weight/importance on each view for fully exploring the complementary information across views. However, most existing weighted MVCs only consider the quality of each view, ignoring the vital role of pseudo label self-supervision information in weight learning. In this work, we propose a novel self-supervised weighted information bottleneck (SWIB) method for solving the multi-view clustering problem. It combines the weighted information from different views based on information bottleneck theory, and the view weight learning mechanism is newly designed by simultaneously taking into accounting both the quality of view-contained information and the self-supervised information on the data partition of each view. Experimental results on multi-view text, multi-feature image, multi-angle video, and multi-modal text-image dataset as well as large-scale datasets show the superiority of the SWIB method. To our knowledge, this is the first work incorporating the self-supervised learning into weighted multi-view clustering.
A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points
PDF ↗Deep reinforcement learning is used in various domains, but usually under the assumption that the environment has stationary conditions like transitions and state distributions. When this assumption is not met, performance suffers. For this reason, tracking continuous environmental changes and adapting to unpredictable conditions is challenging yet crucial because it ensures that systems remain reliable and flexible in practical scenarios. Our research introduces Behavior-Aware Detection and Adaptation (BADA), an innovative framework that merges environmental change detection with behavior adaptation. The key inspiration behind our method is that policies exhibit different global behaviors in changing environments. Specifically, environmental changes are identified by analyzing variations between behaviors using Wasserstein distances without manually set thresholds. The model adapts to the new environment through behavior regularization based on the extent of changes. The results of a series of experiments demonstrate better performance relative to several current algorithms. This research also indicates significant potential for tackling this long-standing challenge.
Exploiting self-supervised learning (SSL) to extract the universal representations of time series could not only capture the natural properties of time series but also offer huge help to the downstream tasks. Nevertheless, existing time series representation learning (TSRL) methods face challenges in attaining universality. Indeed, existing methods relying solely on one SSL strategy (either contrastive learning (CL) or generative) often fall short in capturing rich semantic information for various downstream tasks. Moreover, time series exhibit diverse distributions and inherent characteristics, particularly with the common occurrence of missing values, posing a notable challenge for existing backbones in effectively handling such diverse time series data. To bridge these gaps, we propose CTRL, a framework for universal TSRL. For the first time, we employ Neural Controlled Differential Equation (NCDE) as the backbone for TSRL, which captures the continuous processes and exhibits robustness to missing data. Additionally, a dual-task SSL strategy, integrating both reconstruction and contrasting tasks, is proposed to enrich the semantic information of the learned representations. Furthermore, novel hard negative construction and false negative elimination mechanisms are proposed to improve sampling efficiency and reduce sampling bias in CL. Finally, extensive experiments demonstrate the superiority of CTRL in forecasting, classification, and imputation tasks, particularly its outstanding robustness to missing data.
Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences. Although there are existing attention variants that improve computational efficiency, they have a limited ability to abstract global information effectively based on their hand-crafted mixing strategies. On the other hand, state-space models (SSMs) are tailored for long sequences but cannot capture complicated local information. Therefore, the combination of them as a unified token mixer is a trend in recent long-sequence models. However, the linearized attention degrades performance significantly even when equipped with SSMs. To address the issue, we propose a new method called LongVQ. LongVQ uses the vector quantization (VQ) technique to compress the global abstraction as a length-fixed codebook, enabling the linear-time computation of the attention matrix. This technique effectively maintains dynamic global and local patterns, which helps to complement the lack of long-range dependency issues. Our experiments on the Long Range Arena benchmark, autoregressive language modeling, and image and speech classification demonstrate the effectiveness of LongVQ. Our model achieves significant improvements over other sequence models, including variants of Transformers, Convolutions, and recent State Space Models.
Natural Language Inference (NLI) is a crucial task in natural language processing that involves determining the relationship between two sentences, typically referred to as the premise and the hypothesis. However, traditional NLI models solely rely on the semantic information inherent in independent sentences and lack relevant situational visual information, which can hinder a complete understanding of the intended meaning of the sentences due to the ambiguity and vagueness of language. To address this challenge, we propose an innovative ScenaFuse adapter that simultaneously integrates large-scale pre-trained linguistic knowledge and relevant visual information for NLI tasks. Specifically, we first design an image-sentence interaction module to incorporate visuals into the attention mechanism of the pre-trained model, allowing the two modalities to interact comprehensively. Furthermore, we introduce an image-sentence fusion module that can adaptively integrate visual information from images and semantic information from sentences. By incorporating relevant visual information and leveraging linguistic knowledge, our approach bridges the gap between language and vision, leading to improved understanding and inference capabilities in NLI tasks. Extensive benchmark experiments demonstrate that our proposed ScenaFuse, a scenario-guided approach, consistently boosts NLI performance.