Multi-label Learning with Partial Labels (ML-PL) learns from training data, where each sample is annotated with part of positive labels while leaving the rest of positive labels unannotated. Existing methods mainly focus on extending multi-label losses to estimate unannotated labels, further inducing a missing-robust network. However, training with single network could lead to confirmation bias (i.e., the model tends to confirm its mistakes). To tackle this issue, we propose a novel learning paradigm termed Co-Label Selection (CLS), where two networks feed forward all data and cooperate in a co-training manner for critical label selection. Different from traditional co-training based methods that networks select confident samples for each other, we start from a new perspective that two networks are encouraged to remove false-negative labels while keep training samples reserved. Meanwhile, considering the extreme positive-negative label imbalance in ML-PL that leads the model to focus on negative labels, we enforce the model to concentrate on positive labels by abandoning non-informative negative labels to alleviate such issue. By shifting the cooperation strategy from "Sample Selection'' to "Label Selection'', CLS avoids directly dropping samples and reserves training data in most extent, thus enhancing the utilization of supervised signals and the generalization of the learning model. Empirical results performed on various multi-label datasets demonstrate that our CLS is significantly superior to other state-of-the-art methods.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
This paper targets on the regularization effect of momentum-based methods in regression settings and analyzes the popular diagonal linear networks to precisely characterize the implicit bias of continuous versions of heavy-ball (HB) and Nesterov's method of accelerated gradients (NAG). We show that, HB and NAG exhibit different implicit bias compared to GD for diagonal linear networks, which is different from the one for classic linear regression problem where momentum-based methods share the same implicit bias with GD. Specifically, the role of momentum in the implicit bias of GD is twofold: (a) HB and NAG induce extra initialization mitigation effects similar to SGD that are beneficial for generalization of sparse regression; (b) the implicit regularization effects of HB and NAG also depend on the initialization of gradients explicitly, which may not be benign for generalization. As a result, whether HB and NAG have better generalization properties than GD jointly depends on the aforementioned twofold effects determined by various parameters such as learning rate, momentum factor, and integral of gradients. Our findings highlight the potential beneficial role of momentum and can help understand its advantages in practice such as when it will lead to better generalization performance.
Deep neural networks have become foundational to advancements in multiple domains, including recommendation systems, natural language processing, and so on. Despite their successes, these models often contain incompatible parameters that can be underutilized or detrimental to model performance, particularly when faced with specific, varying data distributions. Existing research excels in removing such parameters or merging the outputs of multiple different pretrained models. However, the former focuses on efficiency rather than performance, while the latter requires several times more computing and storage resources to support inference. In this paper, we set the goal to explicitly improve these incompatible parameters by leveraging the complementary strengths of different models, thereby directly enhancing the models without any additional parameters. Specifically, we propose Compatibility-aware Knowledge Integration (CKI), which consists of Parameter Compatibility Assessment and Parameter Splicing, which are used to evaluate the knowledge content of multiple models and integrate the knowledge into one model, respectively. The integrated model can be used directly for inference or for further fine-tuning. Extensive experiments on various recommendation and language datasets show that CKI can effectively optimize incompatible parameters under multiple tasks and settings to break through the training limit of the original model without increasing the inference cost.
Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading
PDF ↗Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR diagnosis because of the wide coverage of the field of view. Therefore, different from most of the previous single-view DR grading methods, we design a dynamic selection-driven multi-view DR grading method to fit clinical scenarios better. Since lesion information plays a key role in DR diagnosis, previous methods usually boost the model performance by enhancing the lesion feature. However, during the actual diagnosis, ophthalmologists not only focus on the crucial parts, but also exclude irrelevant features to ensure the accuracy of judgment. To this end, we introduce the idea of dynamic selection and design a series of selection mechanisms from fine granularity to coarse granularity. In this work, we first introduce an Ophthalmic Image Reader (OIR) agent to provide the model with pixel-level prompts of suspected lesion areas. Moreover, a Multi-View Token Selection Module (MVTSM) is designed to prune redundant feature tokens and realize dynamic selection of key information. In the final decision stage, we dynamically fuse multi-view features through the novel Multi-View Mixture of Experts Module (MVMoEM), to enhance key views and reduce the impact of conflicting views. Extensive experiments on a large multi-view fundus image dataset with 34,452 images demonstrate that our method performs favorably against state-of-the-art models.
This paper introduces Conformal Thresholded Intervals (CTI), a novel conformal regression method that aims to produce the smallest possible prediction set with guaranteed coverage. Unlike existing methods that rely on nested conformal frameworks and full conditional distribution estimation, CTI estimates the conditional probability density for a new response to fall into each interquantile interval using off-the-shelf multi-output quantile regression. By leveraging the inverse relationship between interval length and probability density, CTI constructs prediction sets by thresholding the estimated conditional interquantile intervals based on their length. The optimal threshold is determined using a calibration set to ensure marginal coverage, effectively balancing the trade-off between prediction set size and coverage. CTI's approach is computationally efficient and avoids the complexity of estimating the full conditional distribution. The method is theoretically grounded, with provable guarantees for marginal coverage and achieving the smallest prediction size given by Neyman-Pearson . Extensive experimental results demonstrate that CTI achieves superior performance compared to state-of-the-art conformal regression methods across various datasets, consistently producing smaller prediction sets while maintaining the desired coverage level. The proposed method offers a simple yet effective solution for reliable uncertainty quantification in regression tasks, making it an attractive choice for practitioners seeking accurate and efficient conformal prediction.
Uncertainty quantification is essential in decision-making, especially when joint distributions of random variables are involved. While conformal prediction provides distribution-free prediction sets with valid coverage guarantees, it traditionally focuses on single predictions. This paper introduces novel conformal prediction methods for estimating the sum or average of unknown labels over specific index sets. We develop conformal prediction intervals for single target to the prediction interval for sum of multiple targets. Under permutation invariant assumptions, we prove the validity of our proposed method. We also apply our algorithms on class average estimation and path cost prediction tasks, and we show that our method outperforms existing conformalized approaches as well as non-conformal approaches.
Existing causal learning algorithms focus on micro-level causal discovery, confronting significant challenges in identifying the influence of macro systems, composed of micro-level variables, on other variables. This difficulty arises because the causal relationships in macro systems are often mediated through micro-level causal interactions, which can lead to erroneous causal discovery or omission when dispersed. To address this issue, we propose the Emergence-inspired Multi-granularity Causal learning (EMCausal) method. Inspired by the emerging phenomena of aggregating micro level variables into macro level representations, EMCausal introduces a progressive mapping encoder to simulate the process, thus capturing the causal relationships driven by these macro entities. Next, it introduces a causal consistency constraint to collaboratively reconstruct micro variables using macro-level representations, enabling the learning of a multi-granular causal structure. Experimental results on both synthetic and real datasets demonstrate that EMCausal can identify causal graphs under the influence of causal emergence, outperforming competitive baselines in term of accuracy and robustness.
This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method.
Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain Adaptation
PDF ↗Multi-source domain adaptation (MSDA), which utilizes multiple source domains to align the distribution of a single target domain, is a popular and challenging setting in domain adaptation (DA). However, existing MSDA approaches are difficult to obtain sufficient target domain knowledge, which serve as the transfer object. Furthermore, the target distributions are confused in the real world, i.e., the model cannot obtain the domain labels of target domains. To tackle these problems, we consider a more realistic DA setting Multi-Source Blended-Target Domain Adaptation (MBDA) and propose an Invertible Projection and Conditional Alignment (IPCA) method. Specifically, to reduce the impact of the distribution discrepancy, we construct an invertible projection for the source and blended-target domains. Then, we adopt a projection consistency regularization to our model, which makes the model more robust on the domain-specific parts. In addition, because the labels of the blended-target domain are unseen, we introduce conditional discrepancy to obtain the domain-level discriminative information and guide the classifier to serve as the discriminator, which is suitable for MBDA settings. Extensive experiment results on the ImageCLEF-DA, Office-Home, and DomainNet datasets validate the effectiveness of our method.
Blended-target domain adaptation (BTDA) leverages learned source knowledge to adapt the model to a blended-target domain that is composed of multiple unlabeled sub-target domains with distinct statistical characteristics. The existing BTDA methods usually overlook semantic correlation information across multiple domains and domain shifts among sub-target domains, resulting in suboptimal adaptation performance. To fully harness semantic knowledge and alleviate domain shifts in hybrid data distribution, we propose a collaborative semantic consistency alignment (CSCA) method for BTDA. Specifically, we achieve distribution alignment by minimizing the sliced Wasserstein distance between the source and target feature distributions. To alleviate complex domain shifts among all sub-target domains in the hybrid feature space, we design graph networks to propagate and share semantic knowledge across domains, which reduces semantic discrepancies among multiple domains. Additionally, we propose a double consistency regularization method to reduce the susceptibility of the model to domain-specific information, further facilitating semantic alignment and alleviating domain shifts. Extensive experiments on several datasets show that CSCA achieves promising classification performance.
Label polysemy, where an instance can be associated with multiple labels, is common in real-world tasks. LDL (label distribution learning) is an effective learning paradigm for handling label polysemy, where each instance is associated with a label distribution. Although numerous LDL algorithms have been proposed and achieved satisfactory performance on most existing datasets, they are typically trained directly on the collected label distributions which often lack quality guarantees in real-world tasks due to annotator subjectivity and algorithm assumptions. Consequently, direct learning from such uncertain label distributions can lead to unpredictable generalization performance. To address this problem, we propose an adaptive-grained label distribution learning framework whose main idea is to extract relatively reliable supervision information from unreliable label distributions, and thus the label distribution learning task can be decomposed into three subtasks: coarsening label distributions, learning coarse-grained labels and refining coarse-grained labels. In this framework, we design an adaptive label coarsening algorithm to extract an optimal coarsen-grained labels and a label refining function to enhance the coarse-grained label into the final label distributions. Finally, we conduct extensive experiments on real-world datasets to demonstrate the advantages of our proposal.
Visual prompt tuning-based continual learning (CL) methods have shown promising performance in exemplar-free scenarios, where their key component can be viewed as a prompt generator. Existing approaches generally rely on freezing old prompts, slow updating and task discrimination for prompt generators to preserve stability and minimize forgetting. In contrast, we introduce a novel approach that trains a consistent prompt generator to ensure stability during CL. Consistency means that for any instance from an old task, its corresponding instance-ware prompt generated by the prompt generator remains consistent even as the generator continually updates in a new task. This ensures that the representation of a specific instance remains stable across tasks and thereby prevents forgetting. We employ a mixture of experts (MoE) as the prompt generator, which contains a router and multiple experts. By deriving conditions sufficient to achieve the consistency for the MoE prompt generator, we demonstrate that: during training in a new task, if the router and experts update in the directions orthogonal to the subspaces spanned by old input features and gating vectors, respectively, the consistency can be theoretically guaranteed. To implement this orthogonality, we project parameter gradients to those orthogonal directions using the orthogonal projection matrices computed via the null space method. Extensive experiments on four class-incremental learning benchmarks validate the effectiveness and superiority of our approach.
Mixup is a data augmentation technique that enhances model generalization by interpolating between data points using a mixing ratio lambda in the image domain. Recently, the concept of mixup has been adapted to the graph domain through node-centric interpolations. However, these approaches often fail to address the complexity of interconnected relationships, potentially damaging the graph's natural topology and undermining node interactions. Furthermore, current graph mixup methods employ a one-size-fits-all strategy with a randomly sampled lambda for all mixup pairs, ignoring the diverse needs of different pairs. This paper proposes an Adaptive Graph Mixup (AGMixup) framework for semi-supervised node classification. AGMixup introduces a subgraph-centric approach, which treats each subgraph similarly to how images are handled in Euclidean domains, thus facilitating a more natural integration of mixup into graph-based learning. We also propose an adaptive mechanism to tune the mixing ratio lambda for diverse mixup pairs, guided by the contextual similarity and uncertainty of the involved subgraphs. Extensive experiments across seven datasets on semi-supervised node classification benchmarks demonstrate AGMixup's superiority over state-of-the-art graph mixup methods.
VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distribution
PDF ↗With the popularity of 3D volumetric video applications, such as Autonomous Driving, Virtual Reality, and Mixed Reality, current developers have turned to deep learning for compressing volumetric video frames, i.e., point clouds for video upstreaming. The latest deep learning-based solutions offer higher efficiency, lower distortion, and better hardware support compared to traditional ones like MPEG and JPEG. However, privacy threats arise, especially reconstruction attacks targeting to recover the original input point cloud from the intermediate results. In this paper, we design VVRec, to the best of our knowledge, which is the first targeting DL-based Volumetric Video Reconstruction attack scheme. VVRec demonstrates the ability to reconstruct high-quality point clouds from intercepted transmission intermediate results using four well-trained neural network modules we design. Leveraging the latest latent diffusion models with Gamma distribution and a refinement algorithm, VVRec excels in reconstruction quality and color recovery and surpasses existing defenses. We evaluate VVRec using three volumetric video datasets. The results demonstrate that VVRec achieves 64.70dB reconstruction accuracy, with an impressive 46.39% reduction of distortion over baselines.
Concept drift, characterized by unpredictable changes in data distribution over time, poses significant challenges to machine learning models in streaming data scenarios. Although error rate-based concept drift detectors are widely used, they often fail to identify drift in the early stages when the data distribution changes but error rates remain constant. This paper introduces the Prediction Uncertainty Index (PU-index), derived from the prediction uncertainty of the classifier, as a superior alternative to the error rate for drift detection. Our theoretical analysis demonstrates that: (1) The PU-index can detect drift even when error rates remain stable. (2) Any change in the error rate will lead to a corresponding change in the PU-index. These properties make the PU-index a more sensitive and robust indicator for drift detection compared to existing methods. We also propose a PU-index-based Drift Detector (PUDD) that employs a novel Adaptive PU-index Bucketing algorithm for detecting drift. Empirical evaluations on both synthetic and real-world datasets demonstrate PUDD’s efficacy in detecting drift in structured and image data.
Federated Learning (FL) mitigates privacy leakage in decentralized machine learning by allowing multiple clients to train collaboratively locally. However, dynamic mobile networks with high mobility, intermittent connectivity, and bandwidth limitation severely hinder model updates to the cloud server. Although previous studies have typically addressed user mobility issue through task reassignment or predictive modeling, frequent migrations may result in high communication overhead. Addressing this challenge involves not only dealing with resource constraints, but also finding ways to mitigate the challenges posed by user migrations. We therefore propose a intertemporal incentive framework, FedCross, which ensures the continuity of FL tasks by migrating interrupted training tasks to feasible mobile devices. FedCross comprises two distinct stages: Specifically, in Stage 1, we address the task allocation problem across regions under resource constraints by employing a multi-objective migration algorithm to quantify the optimal task receivers. Moreover, we adopt evolutionary game theory to capture the dynamic decision-making of users, forecasting the evolution of user proportions across different regions to mitigate frequent migrations. In Stage 2, we utilize a procurement auction mechanism to allocate rewards among base stations, ensuring that those providing high-quality models receive optimal compensation. This approach incentivizes sustained user participation, thereby ensuring the overall feasibility of FedCross. Finally, experimental results validate the theoretical soundness of FedCross and demonstrate its significant reduction in communication overhead.
SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks
PDF ↗Due to the capability of dynamic state space models (SSMs) in capturing long-range dependencies with linear-time computational complexity, Mamba has shown notable performance in NLP tasks. This has inspired the rapid development of Mamba-based vision models, resulting in promising results in visual recognition tasks. However, such models are not capable of distilling features across layers through feature aggregation, interaction, and selection. Moreover, existing cross-layer feature aggregation methods designed for CNNs or ViTs are not practical in Mamba-based models due to high computational costs. Therefore, this paper aims to introduce an efficient cross-layer feature aggregation mechanism for vision backbone networks. Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX to effectively improve cross-layer feature interaction and reuse. Specifically, we build two different types of network layers: ganglion layers and normal layers. The former has higher connectivity and complexity, enabling multi-layer feature aggregation and interaction in an input-dependent manner. In contrast, the latter has lower connectivity and complexity. By interleaving these two types of layers, we design a new family of vision backbone networks with sparsely cross-connected layers, achieving an excellent trade-off among model size, computational cost, memory cost, and accuracy in comparison to its counterparts. For instance, with fewer parameters, SparX-Mamba-T improves the top-1 accuracy of VMamba-T from 82.5% to 83.5%, while SparX-Swin-T achieves a 1.3% increase in top-1 accuracy compared to Swin-T. Extensive experimental results demonstrate that our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.
Multi-view tensor clustering (MVTC) has gained much attention for its effectiveness in capturing global high-order correlations across views. However, current MVTC methods suffer from two limitations: 1) adopting a two-stage process to learn the latent features for clustering, and 2) either ignoring local similarities within views or treating local similarities and global high-order correlations equally. In this paper, we propose a smooth low-rank MVTC (SLR-MVTC) method, which aims to extract latent features that are smooth within each view and low-rank across views, enhancing clustering performance. Specifically, we first learn latent features from each view using orthogonal projection and then construct the latent feature tensor by concatenation and rotation. Then, we introduce a new smooth tensor nuclear norm to depict the low-rank components of the low-frequency parts in the feature tensor. Benefiting from the fast Fourier transform along the sample dimension, the obtained low-frequency components effectively capture local smoothness within views, while their low-rank parts further explore global correlations across views. Experimental results on six multi-view datasets demonstrate that SLR-MVTC outperforms state-of-the-art algorithms in terms of clustering performance and CPU time.
With the advancement of graph representation learning, self-supervised graph contrastive learning (GCL) has emerged as a key technique in the field. In GCL, positive and negative samples are generated through data augmentation. While recent works have introduced model-based methods to enhance positive graph augmentations, they often overlook the importance of negative samples, relying instead on rule-based methods that can fail to capture meaningful graph patterns. To address this issue, we propose a novel model-based adversarial contrastive graph augmentation (ACGA) method that automatically generates both positive graph samples with minimal sufficient information and hard negative graph samples. Additionally, we provide a theoretical framework to analyze the process of positive and negative graph augmentation in self-supervised GCL. We evaluate our ACGA method through extensive experiments on representative benchmark datasets, and the results demonstrate that ACGA outperforms state-of-the-art baselines.
Designing expressive generative models that support exact and efficient inference is a core question in probabilistic ML. Probabilistic circuits (PCs) offer a framework where this tractability-vs-expressiveness trade-off can be analyzed theoretically. Recently, squared PCs encoding subtractive mixtures via negative parameters have emerged as tractable models that can be exponentially more expressive than monotonic PCs, i.e., PCs with positive parameters only. In this paper we provide a more precise theoretical characterization of the expressiveness relationships among these models. First, we prove that squared PCs can be less expressive than monotonic ones. Second, we formalize a novel class of PCs – sum of squares PCs – that can be exponentially more expressive than both squared and monotonic PCs. Around sum of squares PCs, we build an expressiveness hierarchy that allows us to precisely unify and separate different tractable model classes such as Born Machines and PSD models, and other recently introduced tractable probabilistic models by using complex parameters. Finally, we empirically show the effectiveness of sum of squares circuits in performing distribution estimation.