Knowledge editing (KE) provides a scalable approach for updating factual knowledge in large language models without full retraining. While previous studies have demonstrated effectiveness in general domains and medical QA tasks, little attention has been paid to KE in multimodal medical scenarios. Unlike text-only settings, medical KE demands integrating updated knowledge with visual reasoning to support safe and interpretable clinical decisions. To address this gap, we propose MultiMedBench, the first benchmark tailored to evaluating KE in clinical multimodal tasks. Our framework spans both understanding and reasoning task types, defines a three-dimensional metric suite (reliability, generality, and locality), and supports cross-paradigm comparisons across general and domain-specific models. We conduct extensive experiments under single-editing and lifelong-editing settings. Results suggest that current methods struggle with generalization and long-tail reasoning, particularly in complex clinical workflows. We further present an efficiency analysis (e.g., edit latency, memory footprint), revealing practical trade-offs in real-world deployment across KE paradigms. Overall, MultiMedBench not only reveals the limitations of current approaches but also provides a solid foundation for developing clinically robust knowledge editing techniques in the future.

Large Language Models (LLMs) show remarkable potential for few-shot information extraction (IE), yet their performance is highly sensitive to the choice of in-context examples. Conventional selection strategies often fail to provide informative guidance, as they overlook a key source of model fallibility: confusion stemming not just from semantic content, but also from the generation of well-structured formats required by IE tasks. To address this, we introduce Active Prompting for Information Extraction (APIE), a novel active prompting framework guided by a principle we term introspective confusion. Our method empowers an LLM to assess its own confusion through a dual-component uncertainty metric that uniquely quantifies both Format Uncertainty (difficulty in generating correct syntax) and Content Uncertainty (inconsistency in extracted semantics). By ranking unlabeled data with this comprehensive score, our framework actively selects the most challenging and informative samples to serve as few-shot exemplars. Extensive experiments on four benchmarks show that our approach consistently outperforms strong baselines, yielding significant improvements in both extraction accuracy and robustness. Our work highlights the critical importance of a fine-grained, dual-level view of model uncertainty when it comes to building effective and reliable structured generation systems.

We present a novel setting of active learning (AL) where multiple target models are simultaneously learned. This setting arises in real-world applications where machine learning systems require training multiple models on the same labeled dataset to accommodate diverse devices with varying computational resources. However, traditional AL methods are often limited by their model dependence and non-transferability. In this paper, we address the question of whether an effective AL method can be designed for multiple target models. We analyze the query complexity of active and passive learning in this setting and demonstrate the potential for AL to achieve improved query complexity. Based on this insight, we further propose an agnostic AL sampling strategy which selects examples located in the joint disagreement regions of different target models. Experimental evaluations on classification and regression benchmarks validate the effectiveness of our approach over traditional AL methods.

Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data. However, in the context of semi-supervised multi-label learning (SSMLL), conventional pseudo-labeling methods encounter difficulties when dealing with instances associated with multiple labels and an unknown label count. These limitations often result in the introduction of false positive labels or the neglect of true positive ones. To overcome these challenges, this paper proposes a novel solution called Class-distribution-Aware Pseudo-labeling (CAP) that performs pseudo-labeling in a class-aware manner. The proposed approach introduces a regularized learning framework incorporating class-aware thresholds, which effectively control the assignment of positive and negative pseudo-labels for each class. Notably, even with a small proportion of labeled examples, our observations demonstrate that the estimated class distribution serves as a reliable approximation. Motivated by this finding, we develop a class-distribution-aware thresholding (CAT) strategy to ensure the alignment of pseudo-label distribution with the true distribution. Moreover, we extend CAT into a label decision method, aiming to improve the model's classification performance during the testing phase. The correctness of the estimated class distribution is theoretically verified, and a generalization error bound is provided for our proposed method. Extensive experiments on multiple benchmark datasets confirm the efficacy of CAP in addressing the challenges of SSMLL problems.

Existing learning-based visual retouching primarily focuses on improving image quality through end-to-end objective mapping between input and retouched images. However, these approaches often overlook two critical aspects: the progressive nature of image retouching and the subjective aesthetic preferences, resulting in suboptimal visual outcomes. To address this, we introduce Automatic Aesthetic Image Retouching via active reinforcement learning (A$^{3}$3RL) to enhance the visualization experience in two sub-tasks: color enhancement and composition optimization, which are formulated as a unified Markov Decision Process in the proposed A$^{3}$3RL framework. In our approach, each pixel functions as an autonomous agent that determines optimal actions based on aesthetic guidance, engaging in online exploration through immediate pixel-wise and channel-wise feedback from the aesthetic environment. By leveraging a pretrained image aesthetic model, our method ensures that the A$^{3}$3RL process aligns with human aesthetic preferences and adheres to subjective aesthetic principles. The framework integrates pixel-level retouching actions with image-level operations to achieve optimal image sequences through progressive iterations. Extensive experiments demonstrate that our method effectively recalibrates image aesthetics across multiple dimensions: low-level quality metrics (PSNR, SSIM), visual perception (LPIPS), and subjective visual experience (human survey). The results demonstrate high consistency with expert-retouched ground-truth images.

Diffusion-based models have shown great promise in real-world image super-resolution (Real-ISR), but often generate content with structural errors and spurious texture details due to the empirical priors and illusions of these models. To address this issue, we introduce StructSR, a simple, effective, and plug-and-play method that enhances structural fidelity and suppresses spurious details for diffusion-based Real-ISR. StructSR operates without the need for additional fine-tuning, external model priors, or high-level semantic knowledge. At its core is the Structure-Aware Screening (SAS) mechanism, which identifies the image with the highest structural similarity to the low-resolution (LR) input in the early inference stage, allowing us to leverage it as a historical structure knowledge to suppress the generation of spurious details. By intervening in the diffusion inference process, StructSR seamlessly integrates with existing diffusion-based Real-ISR models. Our experimental results demonstrate that StructSR significantly improves the fidelity of structure and texture, improving the PSNR and SSIM metrics by an average of 5.27% and 9.36% on a synthetic dataset (DIV2K-Val) and 4.13% and 8.64% on two real-world datasets (RealSR and DRealSR) when integrated with four state-of-the-art diffusion-based Real-ISR methods.

Long-tailed (LT) data distribution is common in multi-label image classification (MLC) and can significantly impact the performance of classification models. One reason is the challenge of learning unbiased instance representations (i.e. features) for imbalanced datasets. Additionally, the co-occurrence of head/tail classes within the same instance, along with complex label dependencies, introduces further challenges. In this work, we delve into this problem through the lens of neural collapse (NC). NC refers to a phenomenon where the last-layer features and classifier of a deep neural network model exhibit a simplex Equiangular Tight Frame (ETF) structure during its terminal training phase. This structure creates an optimal linearly separable state. However, this phenomenon typically occurs in balanced datasets but rarely applies to the typical imbalanced problem. To induce NC properties under Long-tailed multi-label classification (LT-MLC) conditions, we propose an approach named MLC-NC, which aims to learn high-quality data representations and improve the model’s generalization ability. Specifically, MLC-NC accounts for the fact that different labels correspond to different feature parts located in images. MLC-NC extracts class-wise features from each instance through a cross-attention mechanism. To guide the features toward the ETF structure, we introduce visual-semantic feature alignment with a fixed ETF structured label embedding, which helps to learn evenly distributed class centers. To reduce within-class feature variation, we introduce collapse calibration within a lower-dimensional feature space. To mitigate classification bias, we concatenate features and feed them into a binarized fixed ETF classifier. As an orthogonal approach to existing methods, MLC-NC can be seamlessly integrated into various frameworks. Extensive experiments on widely-used benchmarks demonstrate the effectiveness of our method.

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method called optimum shifting, which changes the parameters of a neural network from a sharp minimum to a flatter one while maintaining the same training loss value. Our method is based on the observation that when the input and output of a neural network are fixed, the matrix multiplications within the network can be treated as systems of under-determined linear equations, enabling adjustment of parameters in the solution space, which can be simply accomplished by solving a constrained optimization problem. Furthermore, we introduce a practical stochastic optimum shifting technique utilizing the neural collapse theory to reduce computational costs and provide more degrees of freedom for optimum shifting. Extensive experiments with various deep neural network architectures on benchmark datasets demonstrate the effectiveness of our method.

Active learning (AL), which iteratively queries the most informative examples from a large pool of unlabeled candidates for model training, faces significant challenges in the presence of open-set classes. Existing methods either prioritize query examples likely to belong to known classes, indicating low epistemic uncertainty (EU), or focus on querying those with highly uncertain predictions, reflecting high aleatoric uncertainty (AU). However, they both yield suboptimal performance, as low EU corresponds to limited useful information, and closed-set AU metrics for unknown class examples are less meaningful. In this paper, we propose an Energy-Based Active Open-Set Annotation (EAOA) framework, which effectively integrates EU and AU to achieve superior performance. EAOA features a (C + 1)-class detector and a target classifier, incorporating an energy-based EU measure and a margin-based energy loss designed for the detector, alongside an energy-based AU measure for the target classifier. Another crucial component is the target-driven adaptive sampling strategy. It first forms a smaller candidate set with low EU scores to ensure closed-set properties, making AU metrics meaningful. Subsequently, examples with high AU scores are queried to form the final query set, with the candidate set size adjusted adaptively. Extensive experiments show that EAOA achieves state-of-the-art performance while maintaining high query precision and low training overhead. The code is available at this link.

Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset, but the achievable performance is fundamentally limited by the coverage of the dataset. The action preference query mechanism leverages expert feedback without requiring environment interaction, enabling performance improvements during offline training while avoiding the cost and risks associated with online fine-tuning. However, existing methods still face significant challenges, both in designing helpful query strategies and in efficiently exploiting the collected preferences. Current approaches typically select queries based solely on the distance between policy actions and dataset actions, and apply naive constraints that compel the policy to remain close to the queried preferences. Such strategies often lead to unstable and inefficient policy updates, and pose challenges for integration with value regularization methods. To address these issues, we propose conservative query and adaptive regularization under uncertainty estimation, a novel and lightweight framework that jointly tackles both the challenges of the preference query and exploitation. Specifically, we first employ the Morse neural network to quantify the uncertainty of the given action relative to the dataset. To facilitate helpful queries, we introduce the uncertainty-driven conservative query mechanism that leverages uncertainty estimation to selectively query actions near the dataset to preserve the stability of Bellman updates. For more effective preference exploitation, we propose the uncertainty-aware adaptive regularization to dynamically modulates the strength of data-level constraints based on the uncertainty of policy actions, enabling the policy to benefit from reliable Bellman updates. We integrate our framework with CQL and perform extensive experiments on the D4RL benchmark. The results demonstrate that our method achieves superior or competitive performance across various tasks.

Partial label learning is a prevalent weakly supervised learning paradigm. Despite the impressive performance achieved by existing methods (e.g., those based on self-training or semi-supervised learning (SSL)), they often suffer from error accumulation or inefficient data utilization. To address these, we aim to actively avoid errors at each training stage and fully leverage information from all available data, encompassing candidate and non-candidate labels. C-FreeMix consists of two stages and performs SSL from a conflict-free perspective. In the warm-up stage, we propose conflict-free negative learning to ensure nontoxic supervision signals along with rapid convergence capability. In the SSL stage, we define a Margin metric to select examples with less ambiguity as labeled ones precisely. Then, MixMatch is adopted with two improvements: label refinement and partial mixup, to utilize all available information. Extensive experiments demonstrate that C-FreeMix outperforms the current state-of-the-art methods.

Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all states. However, due to substantial variations in data quality, the fixed regularization strength often leads to a dilemma: Weak regularization strength fails to address extrapolation errors and value overestimation, while strong regularization strength shifts policy learning toward behavior cloning, impeding potential performance enabled by Bellman updates. To address this issue, we propose the selective state-adaptive regularization method for offline RL. Specifically, we introduce state-adaptive regularization coefficients to trust state-level Bellman-driven results, while selectively applying regularization on high-quality actions, aiming to avoid performance degradation caused by tight constraints on low-quality actions. By establishing a connection between the representative value regularization method, CQL, and explicit policy constraint methods, we effectively extend selective state-adaptive regularization to these two mainstream offline RL approaches. Extensive experiments demonstrate that the proposed method significantly outperforms the state-of-the-art approaches in both offline and offline-to-online settings on the D4RL benchmark. The implementation is available at https://github.com/QinwenLuo/SSAR.

Federated Active Learning (FAL) aims to learn an effective global model, while minimizing label queries. Owing to privacy requirements, it is challenging to design effective active data selection schemes due to the lack of cross-client query information. In this paper, we bridge this important gap by proposing the Federated Active data selection by LEverage score sampling (FALE) method. It is designed for regression tasks in the presence of non-i.i.d. client data to enable the server to select data globally in a privacy-preserving manner. Based on FedSVD, FALE aims to estimate the utility of unlabeled data and perform data selection via leverage score sampling. Besides, a secure model learning framework is designed for federated regression tasks to exploit supervision. FALE can operate without requiring an initial labeled set and select the instances in a single pass, significantly reducing communication overhead. Theoretical analyze establishes the query complexity for FALE to achieve constant factor approximation and relative error approximation. Extensive experiments on 11 benchmark datasets demonstrate significant improvements of FALE over existing state-of-the-art methods.

In Federated Learning (FL), the decentralized nature of client training introduces vulnerabilities, notably backdoor attacks. Prevailing anomaly detection approaches typically perform binary classification, dividing clients into trusted and untrusted groups. However, these methods face two critical challenges: the insider threat, where malicious clients concealed within the trusted group compromise the global model, and the benign exclusion, where legitimate contributions from benign clients are mistakenly classified as untrusted and disregarded. These issues weaken both the robustness and fairness of FL systems, exposing inherent defense vulnerabilities. To address these challenges, we propose FedDLAD, a Federated Learning Dual-Layer Anomaly Detection framework designed to enhance resilience against backdoor attacks. The framework leverages the Connectivity-Based Outlier Factor (COF) module to perform a robust initial classification of clients by analyzing structural data connectivity. The Interquartile Range (IQR) module further reinforces this by mitigating the insider threat through the removal of residual malicious influences within the trusted group. Furthermore, the Pardon module dynamically reintegrates misclassified benign clients from the untrusted group, thereby preserving their valuable contributions and addressing the benign exclusion. We conduct extensive evaluations of FedDLAD against state-of-the-art defenses on real-world datasets, demonstrating its superior ability to reduce backdoor attack success rates while maintaining robust model performance. Code is available at: https://github.com/dingbinb/FedDLAD.

The need to generalize the pre-trained deep learning models to unknown test-time data distributions has spurred research into test-time adaptation (TTA). Existing studies have mainly focused on closed-set TTA with only covariate shifts, while largely overlooking open-set TTA that involves semantic shifts, i.e., unknown open-set classes. However, addressing adaptation to unknown classes is crucial for open-world safety-critical applications such as autonomous driving. In this paper, we emphasize that accurate identification of the open-set samples is rather challenging in TTA. The entanglement of semantic shift and covariate shift mutually confuse the network’s discriminative capability. This co-interference further exacerbates considering the single-pass data nature and low latency requirements. With this under standing, we propose Dual-mode Matching and Prompt-based Open Set Adaptation (DM-POSA) for open-set TTA to enhance discriminative feature learning and unknown classes distinguishment with minimal time cost. DM-POSA identifies open-set samples via dual-mode matching strategies, including model-parameter-based and feature space-based matching. It also optimizes the model with a random pairing discrepancy loss, enhancing the distributional difference between open-set and closed-set samples, thus improving the model’s ability to recognize unknown categories. Extensive experiments show the superiority of DM-POSA over state-of-the-art baselines on both closed-set class adaptation and open-set class detection.

Federated learning (FL) enables distributed collaborative learning across local clients while preserving data privacy. However, its practical application in weakly supervised learning (WSL), where only a small subset of data is labeled, remains underexplored. Active learning (AL) is a promising solution for label-limited scenarios, but its adaptation to federated settings presents unique challenges, such as data heterogeneity and noise. In this paper, we propose Inconsistency-based Federated Active Learning (IFAL), a novel approach to address these challenges. First, we introduce a data-driven probability formulation that aligns the biases between local and global models in heterogeneous FL settings. Next, to mitigate noise, we propose an inter-model inconsistency criterion that filters out noisy examples and focuses on those with beneficial prediction discrepancies. Additionally, we introduce an intra-model inconsistency criterion to query examples that help refine the model’s decision boundaries. By combining these strategies with clustering, IFAL effectively selects a diverse and informative query set. Extensive experiments on benchmark datasets demonstrate that IFAL outperforms state-of-the-art methods.

Large language models (LLMs) have demonstrated significant potential in code generation tasks. However, there remains a performance gap between open-source and closed-source models. To address this gap, existing approaches typically generate large amounts of synthetic data for fine-tuning, which often leads to inefficient training. In this work, we propose a data selection strategy in order to improve the effectiveness and efficiency of training for code-based LLMs. By prioritizing data complexity and ensuring that the sampled subset aligns with the distribution of the original dataset, our sampling strategy effectively selects high-quality data. Additionally, we optimize the tokenization process through a "dynamic pack" technique, which minimizes padding tokens and reduces computational resource consumption. Experimental results show that when training on 40% of the OSS-Instruct dataset, the DeepSeek-Coder-Base-6.7B model achieves an average performance of 66.9%, surpassing the 66.1% performance with the full dataset. Moreover, training time is reduced from 47 minutes to 34 minutes, and the peak GPU memory usage decreases from 61.47 GB to 42.72 GB during a single epoch. Similar improvements are observed with the CodeLlama-Python-7B model on the Evol-Instruct dataset. By optimizing both data selection and tokenization, our approach not only improves model performance but also enhances training efficiency.

Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would obscure certain indispensable information. To address this issue, it is intuitive to additionally introduce a logit-level loss function as a supplement to the widely used probability-level loss function, for exploiting the latent information of logits. Unfortunately, we empirically find that the amalgamation of the newly introduced logit-level loss and the previous probability-level loss will lead to performance degeneration, even trailing behind the performance of employing either loss in isolation. We attribute this phenomenon to the collapse of the classification head, which is verified by our theoretical analysis based on the neural collapse theory. Specifically, the gradients of the two loss functions exhibit contradictions in the linear classifier yet display no such conflict within the backbone. Drawing from the theoretical analysis, we propose a novel method called dual-head knowledge distillation, which partitions the linear classifier into two classification heads responsible for different losses, thereby preserving the beneficial effects of both losses on the backbone while eliminating adverse influences on the classification head. Extensive experiments validate that our method can effectively exploit the information inside the logits and achieve superior performance against state-of-the-art counterparts

Federated learning (FL) enables multiple clients to collaboratively train machine learning models under the coordination of a central server, while maintaining privacy. However, the server cannot directly monitor the local training processes, leaving room for malicious clients to introduce backdoors into the model. Research has shown that backdoor attacks exploit specific neurons that are activated only by malicious inputs, remaining dormant with clean data. Building on this insight, we propose a novel defense method called Flipping Weight Updates of Low-Activation Input Neurons (FLAIN) to counter backdoor attacks in FL. Specifically, upon the completion of global training, we use an auxiliary dataset to identify low-activation input neurons and iteratively flip their associated weight updates. This flipping process continues while progressively raising the threshold for low-activation neurons, until the model's performance on the auxiliary data begins to degrade significantly. Extensive experiments demonstrate that FLAIN effectively reduces the success rate of backdoor attacks across a variety of scenarios,including Non-IID data distributions and high malicious client ratios (MCR), while maintaining minimal impact on the performance of clean data. The source code is available at: FLAIN.

Object–context shortcuts remain a persistent challenge in vision‑language models, undermining zero‑shot reliability when test-time scenes diverge from familiar training co-occurrences. We recast this issue as a causal inference problem and ask: Would the prediction remain if the object appeared in a different environment? To answer it at inference time, we estimate object and background expectations within CLIP’s representation space, and synthesize counterfactual embeddings by recombining object features with diverse alternative contexts sampled from external datasets, batch neighbors, or text-derived descriptions. By estimating the Total Direct Effect and simulating intervention, we further subtract background‑only activation, preserving beneficial object–context interactions while mitigating hallucinated scores. Without retraining or prompt design, our method substantially improves both worst-group and average accuracy on context-sensitive benchmarks, establishing a new zero‑shot state of the art. Beyond performance, our framework provides a lightweight representation-level counterfactual approach, offering a practical causal avenue for debiased and reliable multimodal reasoning.

Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not often considered in standard benchmarks for CL. Unlike with the rehearsal mechanism in buffer-based strategies, where sample repetition is controlled by the strategy, repetition in the data stream naturally stems from the environment. This report provides a summary of the CLVision challenge at CVPR 2023, which focused on the topic of repetition in class-incremental learning. The report initially outlines the challenge objective and then describes three solutions proposed by finalist teams that aim to effectively exploit the repetition in the stream to learn continually. The experimental results from the challenge highlight the effectiveness of ensemble-based solutions that employ multiple versions of similar modules, each trained on different but overlapping subsets of classes. This report underscores the transformative potential of taking a different perspective in CL by employing repetition in the data stream to foster innovative strategy design. • An overview of the continual learning challenge of the CLVision workshop at CVPR 2023. • Novel benchmarks focussing on the topic of repetition in continual learning. • Description and discussion of the strategies submitted by the winning teams. • The results highlight the remarkable effectiveness of ensemble-based solutions.

Evaluating the performance of low-light image enhancement (LLE) is highly subjective, thus making integrating human preferences into LLE a necessity. Existing methods fail to consider this and present a series of potentially valid heuristic criteria for training LLE models. In this paper, we propose a new paradigm, i.e., aesthetics-guided low-light image enhancement (ALL-E), which introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Each pixel, functioning as an agent, refines itself by recursive actions. We further present ALL-E+, an extended version of ALL-E, which casts a two-stage aesthetics-guided enhancement and denoising. ALL-E+ achieves low-light enhancement and denoising compensation sequentially in a unified framework, resulting in significant improvements in both subjective visual experience and objective evaluation. Extensive experiments show that integrating aesthetic preferences can further improve the visual experience of enhanced images. Our results on various benchmarks also demonstrate the superiority of our method over state-of-the-art methods.

When taking images against strong light sources, the resulting images often contain heterogeneous flare artifacts. These artifacts can significantly affect image visual quality and downstream computer vision tasks. While collecting real data pairs of flare-corrupted/flare-free images for training flare removal models is challenging, current methods utilize the direct-add approach to synthesize training data. However, these methods do not consider automatic exposure and tone mapping in the image signal processing pipeline (ISP), leading to the limited generalization capability of deep model training using such data. Besides, existing light source recovery methods hardly recover multiple light sources due to the different sizes, shapes, and illuminance of various light sources. In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP, remodeling the principle of automatic exposure in the synthesis pipeline, and designing a more reliable light source recovery strategy. The new pipeline approaches realistic imaging by discriminating the local and global illumination through a convex combination, avoiding global illumination shifting and local over-saturation. Moreover, the current deep models are only generalized to specific devices due to the diversity of cameras' ISPs. To achieve better generalization on different devices, we formulate the generalization problem as an adversarial training problem and embed an adversarial curve learning (ACL) paradigm in the synthesis pipeline to gain better performance. For recovering multiple light sources, our strategy convexly averages the input and output of the neural network based on illuminance levels, thereby avoiding the need for a hard threshold in identifying light sources. We also contribute a new flare removal testing dataset containing the flare-corrupted images captured by fifteen types of consumer electronics. The dataset facilitates the verification of the generalization capability of flare removal methods. Extensive experiments show that our solution can effectively improve the performance of lens flare removal and push the frontier toward more general situations.

Noisy label learning (NLL) in open-world scenarios poses a novel challenge due to the presence of noisy data from both known and unknown classes. Most existing methods operate under the closed-set assumption, rendering them vulnerable to open-set noise, which significantly degrades their performance. While some approaches attempt to mitigate the impact of open-set examples, they struggle to learn effective discriminative representations for them, leading to unsatisfactory recognition performance. To address these issues, we propose a unified Open Adapter (OpenAda) that identifies open-set noise from both data-centric and learning-based perspectives, and can be easily integrated into mainstream NLL methods to improve their performance and robustness. Specifically, the data-centric part leverages label clusterability to sequentially identify basic clean and basic open-set examples both with high neighbor agreement. The learning-based part integrates one-vs-all classifiers with a progressive open disambiguation strategy to learn a reliable “inlier vs. outlier” boundary for each class. This enables the model to detect challenging open-set examples that partially overlap in the representation space with closed-set ones. Extensive experiments on synthetic and real-world datasets validate the superiority of our approach. Notably, with minor modifications, DivideMix with OpenAda achieves performance improvements of 9.31% and 18.26% on the open-world CIFAR-80 dataset under 80% symmetric noise and 40% asymmetric noise. The code is available athttps://github.com/chenchenzong/OpenAda.

In recent years, image segmentation has made significant progress, but acquiring annotated data is still a considerable challenge, especially in remote sensing imagery (RSI). The complex structure and inter-category confusion of RSI increase the time-consuming and cost of pixel-level annotation, and noisy annotations inevitably appear. This paper proposes a boundary-aware knowledge distillation method (BAKD) to handle noisy annotations by evaluating their uncertainty. BAKD consists of two core strategies: Predictive Confidence Evaluation (PCE) and Boundary-annotated Reliability Evaluation (BRE). The predictive confidence jointly decided by the teacher and student networks reflects the annotation’s uncertainty. The boundary-annotated reliability directly measures the annotation’s uncertainty based on the distance from the annotation to the semantic boundary. Leveraging these two types of uncertainty information, BAKD assigns each sample a comprehensive boundary-aware weight to identify samples with potential noisy annotations. This alleviates the impact of noisy annotation on the model’s training and improves its generalization performance. Experimental results show that BAKD achieves competitive semantic segmentation performance on the Potsdam and Vaihingen benchmarks compared with the state-of-the-art KD methods. In addition, BAKD can be easily integrated into semantic segmentation methods based on KD, extending their applicability in handling noisy annotations. Codes are available at https://github.com/sunyueue/BAKD.git.

Remote sensing image classification refers to the task that using algorithms to categorize satellite or aerial imagery into different land cover types. In the real world, long-tailed data distribution is commonly present in remote sensing image classification tasks, causing models to excessively favor sufficient head classes during training and degrading prediction accuracy for scarce tail classes. Although existing methods such as resampling and re-weighting can alleviate the issue of data imbalance to a certain extent, they struggle to sufficiently enhance the diversity of tail class samples. In recent years, some works have begun to use diffusion models to generate diverse samples to balance the class distribution. However, these approaches often overlook the distribution inconsistency between generated and real images, which will hinder the improvement of model performance. To tackle these challenges, this paper proposes a novel diffusion-noise-based augmentation method (DONA) with a two-stage training process. Before training, our specially designed conditional prompts are used together with the original training set to guide the diffusion model in image generation. Furthermore, we propose two strategies to effectively leverage the generated images, which are applied respectively at the end of the first training stage and during the second training stage. First, we design DiffCam-Mix to fuse the background of the generated data with the foreground of the original data, preserving the essential information of the original real images while incorporating the diversity of the generated ones. Second, we use cosine similarity to minimize the differences between the mixed data and their corresponding original data, further calibrating the distribution of different samples. Extensive experiments on three public datasets—SIRI-WHU-LT, PatternNet-LT, and RSI-CB256-LT—demonstrate the effectiveness of the proposed method.

Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise. However, a more common scenario in the real world is the presence of both open-set and closed-set noise. Existing methods typically identify and handle these two types of label noise separately by designing a specific strategy for each type. However, in many real-world scenarios, it would be challenging to identify open-set examples, especially when the dataset has been severely corrupted. Unlike the previous works, we explore how models behave when faced with open-set examples, and find that a part of open-set examples gradually get integrated into certain known classes, which is beneficial for the separation among known classes. Motivated by the phenomenon, we propose a novel two-step contrastive learning method CECL (Class Expansion Contrastive Learning) which aims to deal with both types of label noise by exploiting the useful information of open-set examples. Specifically, we incorporate some open-set examples into closed-set classes to enhance performance while treating others as delimiters to improve representative ability. Extensive experiments on synthetic and real-world datasets with diverse label noise demonstrate the effectiveness of CECL.

Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs). Existing approaches address this issue through loss correction or example selection methods. However, these methods often rely on the model's predictions obtained from the softmax function, which can be over-confident and unreliable. In this study, we identify the translation invariance of the softmax function as the underlying cause of this problem and propose the \textit{Dirichlet-based Prediction Calibration} (DPC) method as a solution. Our method introduces a calibrated softmax function that breaks the translation invariance by incorporating a suitable constant in the exponent term, enabling more reliable model predictions. To ensure stable model training, we leverage a Dirichlet distribution to assign probabilities to predicted labels and introduce a novel evidence deep learning (EDL) loss. The proposed loss function encourages positive and sufficiently large logits for the given label, while penalizing negative and small logits for other labels, leading to more distinct logits and facilitating better example selection based on a large-margin criterion. Through extensive experiments on diverse benchmark datasets, we demonstrate that DPC achieves state-of-the-art performance. The code is available at https://github.com/chenchenzong/DPC.

Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally expensive, particularly for deep models. In this paper, we propose a one-shot AL method to address this challenge, which performs all label queries without repeated model training. Specifically, we extract different representations of the same dataset using distinct network backbones, and actively learn the linear prediction layer on each representation via an $\ell_p$-regression formulation. The regression problems are solved approximately by sampling and reweighting the unlabeled instances based on their maximum Lewis weights across the representations. An upper bound on the number of samples needed is provided with a rigorous analysis for $p\in [1, +\infty)$. Experimental results on 11 benchmarks show that our one-shot approach achieves competitive performances with the state-of-the-art AL methods for multiple target models.

Active learning (AL) has achieved great success by selecting the most valuable examples from unlabeled data. However, they usually deteriorate in real scenarios where open-set noise gets involved, which is studied as open-set annotation (OSA). In this paper, we owe the deterioration to the unreliable predictions arising from softmax-based translation invariance and propose a Dirichlet-based Coarse-to-Fine Example Selection (DCFS) strategy accordingly. Our method introduces simplex-based evidential deep learning (EDL) to break translation invariance and distinguish known and unknown classes by considering evidence-based data and distribution uncertainty simultaneously. Furthermore, hard known-class examples are identified by model discrepancy generated from two classifier heads, where we amplify and alleviate the model discrepancy respectively for unknown and known classes. Finally, we combine the discrepancy with uncertainties to form a two-stage strategy, selecting the most informative examples from known classes. Extensive experiments on various openness ratio datasets demonstrate that DCFS achieves state-of-art performance.

The key to multi-label image classification (MLC) is to improve model performance by leveraging label correlations. Unfortunately, it has been shown that overemphasizing co-occurrence relationships can cause the overfitting issue of the model, ultimately leading to performance degradation. In this paper, we provide a causal inference framework to show that the correlative features caused by the target object and its co-occurring objects can be regarded as a mediator, which has both positive and negative impacts on model predictions. On the positive side, the mediator enhances the recognition performance of the model by capturing co-occurrence relationships; on the negative side, it has the harmful causal effect that causes the model to make an incorrect prediction for the target object, even when only co-occurring objects are present in an image. To address this problem, we propose a counterfactual reasoning method to measure the total direct effect, achieved by enhancing the direct effect caused only by the target object. Due to the unknown location of the target object, we propose patching-based training and inference to accomplish this goal, which divides an image into multiple patches and identifies the pivot patch that contains the target object. Experimental results on multiple benchmark datasets with diverse configurations validate that the proposed method can achieve state-of-the-art performance.

The goal of semi-supervised multi-label learning (SSMLL) is to improve model performance by leveraging the information of unlabeled data. Recent studies usually adopt the pseudo-labeling strategy to tackle unlabeled data based on the assumption that labeled and unlabeled data share the same distribution. However, in realistic scenarios, unlabeled examples are often collected through cost-effective methods, inevitably introducing out-of-distribution (OOD) data, leading to a significant decline in model performance. In this paper, we propose a safe semi-supervised multi-label learning framework based on the theory of evidential deep learning (EDL), with the goal of achieving robust and effective unlabeled data exploitation. On one hand, we propose the asymmetric beta loss to not only compensate for the lack of robustness in common MLL losses, but also to solve the inherent positive-negative imbalance problem faced by the EDL losses in MLL. On the other hand, to construct a robust SSMLL framework, we adopt a dual-head structure to generate class probabilities and instance uncertainties. The former are used to generate pseudo-labels, while the latter are utilized to filter OOD examples. To avoid the need for threshold estimation, we develop a dual-measurement weighted loss function to safely perform unlabeled training. Extensive experiments on multiple benchmark datasets verify the effectiveness of the proposed method in both OOD detection and SSMLL tasks.

Offline-to-online (O2O) reinforcement learning (RL) provides an effective means of leveraging an offline pre-trained policy as initialization to improve performance rapidly with limited online interactions. Recent studies often design fine-tuning strategies for a specific offline RL method and cannot perform general O2O learning from any offline method. To deal with this problem, we disclose that there are evaluation and improvement mismatches between the offline dataset and the online environment, which hinders the direct application of pre-trained policies to online fine-tuning. In this paper, we propose to handle these two mismatches simultaneously, which aims to achieve general O2O learning from any offline method to any online method. Before online fine-tuning, we re-evaluate the pessimistic critic trained on the offline dataset in an optimistic way and then calibrate the misaligned critic with the reliable offline actor to avoid erroneous update. After obtaining an optimistic and and aligned critic, we perform constrained fine-tuning to combat distribution shift during online learning. We show empirically that the proposed method can achieve stable and efficient performance improvement on multiple simulated tasks when compared to the state-of-the-art methods.

Graph collaborative filtering (GCF) has achieved great success in recommender systems due to its ability in mining high-order collaborative signals from historical user-item interactions. However, GCF's performance could be severely affected by the intrinsic noise within the user-item interactions. To this end, several denoised GCF frameworks have been proposed, whose heart is to estimate and handle the reliability of existing interactions. However, most of them suffer from two limitations: 1) the reliability computation itself is noisy, and 2) the reliability threshold is difficult to determine. To address the two limitations, in this paper, we propose a newNeighborhood-informedDenoising framework NiDen for GCF. Specifically, for an existing user-item interaction, NiDen first estimates its reliability by employing the neighborhood information of the user and the item, and then determines whether the interaction is noisy or not via a dynamic thresholding strategy. After that, NiDen mitigates the negative impact of noise by both structure denoising and sample re-weighting. We instantiate NiDen on two representative GCF models and conduct extensive experiments on four widely-used datasets. The results show that NiDen achieves the best performance compared to the existing denoising methods, especially on datasets with heavy noise.

Multi-label image classification relies on a large-scale, well-maintained dataset, which may easily be mislabeled due to various subjective reasons. Existing methods for coping with noise usually focus on improving the model robustness in the case of single-label noise. However, compared with noisy single-label learning, noisy multi-label learning is more practical and challenging. To reduce the negative impact of noisy multi-annotations, we propose a universal approach for noisy multi-label learning (UNM). In UNM, we propose the label-wise embedding network which investigates the semantic alignment between label embeddings and their corresponding output features to learn robust feature representations. Meanwhile, mining the co-occurrence of multi-labels is also added to regularize the noisy network predictions. We cyclically change the fitting status of our label-wise embedding network to distinguish the noisy samples and generate pseudo labels for them. As a result, UNM provides an effective way to exploit the label-wise features and semantic label embeddings in noisy scenarios. To verify the generalizability of our method, we also test our method on Partial Multi-label Learning (PML) and Multi-label Learning with Missing Labels (MLML). Extensive experiments on benchmark datasets including Microsoft COCO, Pascal VOC, and Visual Genome explicitly validate the proposed method.

Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems, but they are still trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit stochastic gradient descent (ISGD) method to train PINNs for improving the stability of training process. We heuristically analyze how ISGD overcome stiffness in the gradient flow dynamics of PINNs, especially for problems with multi-scale solutions. We theoretically prove that for two-layer fully connected neural networks with large hidden nodes, randomly initialized ISGD converges to a globally optimal solution for the quadratic loss function. Empirical results demonstrate that ISGD works well in practice and compares favorably to other gradient-based optimization methods such as SGD and Adam, while can also effectively address the numerical stiffness in training dynamics via gradient descent.

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning. However, these methods can hardly be extended to the multi-label learning scenario, where each instance is associated with multiple semantic labels, because the prediction probabilities do not sum to one and feature maps of the whole example may ignore minor classes in such a scenario. In this paper, we propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems; on the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings. Experimental results on multiple benchmark datasets validate that the proposed method can avoid knowledge counteraction among labels, thus achieving superior performance against diverse comparing methods. Our code is available at: https://github.com/penghui-yang/L2D.

When taking images against strong light sources, the resulting images often contain heterogeneous flare artifacts. These artifacts can importantly affect image visual quality and downstream computer vision tasks. While collecting real data pairs of flare-corrupted/flare-free images for training flare removal models is challenging, current methods utilize the direct-add approach to synthesize data. However, these methods do not consider automatic exposure and tone mapping in image signal processing pipeline (ISP), leading to the limited generalization capability of deep models training using such data. Besides, existing methods struggle to handle multiple light sources due to the different sizes, shapes and illuminance of various light sources. In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy. The new pipeline approaches realistic imaging by discriminating the local and global illumination through convex combination, avoiding global illumination shifting and local over-saturation. Our strategy for recovering multiple light sources convexly averages the input and output of the neural network based on illuminance levels, thereby avoiding the need for a hard threshold in identifying light sources. We also contribute a new flare removal testing dataset containing the flare-corrupted images captured by ten types of consumer electronics. The dataset facilitates the verification of the generalization capability of flare removal methods. Extensive experiments show that our solution can effectively improve the performance of lens flare removal and push the frontier toward more general situations.

Evaluating the performance of low-light image enhancement (LLE) is highly subjective, thus making integrating human preferences into image enhancement a necessity. Existing methods fail to consider this and present a series of potentially valid heuristic criteria for training enhancement models. In this paper, we propose a new paradigm, i.e., aesthetics-guided low-light image enhancement (ALL-E), which introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Each pixel, functioning as an agent, refines itself by recursive actions, i.e., its corresponding adjustment curve is estimated sequentially. Extensive experiments show that integrating aesthetic assessment improves both subjective experience and objective evaluation. Our results on various benchmarks demonstrate the superiority of ALL-E over state-of-the-art methods. Source code: https://dongl-group.github.io/project pages/ALLE.html

Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data. However, in the context of semi-supervised multi-label learning (SSMLL), conventional pseudo-labeling methods encounter difficulties when dealing with instances associated with multiple labels and an unknown label count. These limitations often result in the introduction of false positive labels or the neglect of true positive ones. To overcome these challenges, this paper proposes a novel solution called Class-Aware Pseudo-Labeling (CAP) that performs pseudo-labeling in a class-aware manner. The proposed approach introduces a regularized learning framework incorporating class-aware thresholds, which effectively control the assignment of positive and negative pseudo-labels for each class. Notably, even with a small proportion of labeled examples, our observations demonstrate that the estimated class distribution serves as a reliable approximation. Motivated by this finding, we develop a class-distribution-aware thresholding strategy to ensure the alignment of pseudo-label distribution with the true distribution. The correctness of the estimated class distribution is theoretically verified, and a generalization error bound is provided for our proposed method. Extensive experiments on multiple benchmark datasets confirm the efficacy of CAP in addressing the challenges of SSMLL problems.

Class-conditional noise commonly exists in machine learning tasks, where the class label is corrupted with a probability depending on its ground-truth. Many research efforts have been made to improve the model robustness against the class-conditional noise. However, they typically focus on the single label case by assuming that only one label is corrupted. In real applications, an instance is usually associated with multiple labels, which could be corrupted simultaneously with their respective conditional probabilities. In this paper, we formalize this problem as a general framework of learning with Class-Conditional Multi-label Noise (CCMN for short). We establish two unbiased estimators with error bounds for solving the CCMN problems, and further prove that they are consistent with commonly used multi-label loss functions. Finally, a new method for partial multi-label learning is implemented with the unbiased estimator under the CCMN framework. Empirical studies on multiple datasets and various evaluation metrics validate the effectiveness of the proposed method.

Recent aerial object detection models rely on a large amount of labeled training data, which requires unaffordable manual labeling costs in large aerial scenes with dense objects. Active learning effectively reduces the data labeling cost by selectively querying the informative and representative unlabelled samples. However, existing active learning methods are mainly with class-balanced settings and image-based querying for generic object detection tasks, which are less applicable to aerial object detection scenarios due to the long-tailed class distribution and dense small objects in aerial scenes. In this paper, we propose a novel active learning method for cost-effective aerial object detection. Specifically, both object-level and image-level informativeness are considered in the object selection to refrain from redundant and myopic querying. Besides, an easy-to-use class-balancing criterion is incorporated to favor the minority objects to alleviate the long-tailed class distribution problem in model training. We further devise a training loss to mine the latent knowledge in the unlabeled image regions. Extensive experiments are conducted on the DOTA-v1.0 and DOTA-v2.0 benchmarks to validate the effectiveness of the proposed method. For the ReDet, KLD, and SASM detectors on the DOTA-v2.0 dataset, the results show that our proposed MUS-CDB method can save nearly 75% of the labeling cost while achieving comparable performance to other active learning methods in terms of mAP. Code is publicly online.

Object detection requires plentiful data annotated with bounding boxes for model training. However, in many applications, it is difficult or even impossible to acquire a large set of labeled examples for the target task due to the privacy concern or lack of reliable annotators. On the other hand, due to the high-quality image search engines, such as Flickr and Google, it is relatively easy to obtain resource-rich unlabeled datasets, whose categories are a superset of those of target data. In this article, to improve the target model with cost-effective supervision from source data, we propose a partial transfer learning approach QBox to actively query labels for bounding boxes of source images. Specifically, we design two criteria, i.e., informativeness and transferability, to measure the potential utility of a bounding box for improving the target model. Based on these criteria, QBox actively queries the labels of the most useful boxes from the source domain and, thus, requires fewer training examples to save the labeling cost. Furthermore, the proposed query strategy allows annotators to simply labeling a specific region, instead of the whole image, and, thus, significantly reduces the labeling difficulty. Extensive experiments are performed on various partial transfer benchmarks and a real COVID-19 detection task. The results validate that QBox improves the detection accuracy with lower labeling cost compared to state-of-the-art query strategies for object detection.

Existing active learning studies typically work in the closed-set setting by assuming that all data examples to be labeled are drawn from known classes. However, in real annotation tasks, the unlabeled data usually contains a large amount of examples from unknown classes, resulting in the failure of most active learning methods. To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation. The LfOSA framework introduces an auxiliary network to model the perexample max activation value (MAV) distribution with a Gaussian Mixture Model, which can dynamically select the examples with highest probability from known classes in the unlabeled set. Moreover, by reducing the temperature T of the loss function, the detection model will be further optimized by exploiting both known and unknown supervision. The experimental results show that the proposed method can significantly improve the selection quality of known classes, and achieve higher classification accuracy with lower annotation cost than state-of-the-art active learning methods. To the best of our knowledge, this is the first work of active learning for open-set annotation.

We describe and explore a novel setting of active learning (AL), where there are multiple target models to be learned simultaneously. In many real applications, the machine learning system is required to be deployed on diverse devices with varying computational resources (e.g., workstation, mobile phone, edge devices, etc.), which leads to the demand of training multiple target models on the same labeled dataset. However, it is generally believed that AL is model-dependent and untransferable, i.e., the data queried by one model may be less effective for training another model. This phenomenon naturally raises a question "Does there exist an AL method that is effective for multiple target models?" In this paper, we answer this question by theoretically analyzing the label complexity of active and passive learning under the setting with multiple target models, and conclude that AL does have potential to achieve better label complexity under this novel setting. Based on this insight, we further propose an agnostic AL sampling strategy to select the examples located in the joint disagreement regions of different target models. The experimental results on the OCR benchmarks show that the proposed method can significantly surpass the traditional active and passive learning methods under this challenging setting.

Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability, however, is challenged in this paper. We identify a novel threat model named stability attack, which aims to hinder robust availability by slightly manipulating the training data. Under this threat, we show that adversarial training using a conventional defense budget $\epsilon$ provably fails to provide test robustness in a simple statistical setting, where the non-robust features of the training data can be reinforced by $\epsilon$-bounded perturbation. Further, we analyze the necessity of enlarging the defense budget to counter stability attacks. Finally, comprehensive experiments demonstrate that stability attacks are harmful on benchmark datasets, and thus the adaptive defense is necessary to maintain robustness.

In single positive multi-label learning (SPML), only one of multiple positive labels is observed for each instance. The previous work trains the model by simply treating unobserved labels as negative ones, and designs the regularization to constrain the number of expected positive labels. However, in many real-world scenarios, the true number of positive labels is unavailable, making such methods less applicable. In this paper, we propose to solve SPML problems by designing a Label-Aware global Consistency (LAC) regularization, which leverages the manifold structure information to enhance the recovery of potential positive labels. On one hand, we first perform pseudo-labeling for each unobserved label based on its prediction probability. The consistency regularization is then imposed on model outputs to balance the fitting of identified labels and exploring of potential positive labels. On the other hand, by enforcing label-wise embeddings to maintain global consistency, LAC loss encourages the model to learn more distinctive representations, which is beneficial for recovering the information of potential positive labels. Experiments on multiple benchmark datasets validate that the proposed method can achieve state-of-the-art performance for solving SPML tasks.

Partial multi-label learning (PML) deals with problems where each instance is assigned with a candidate label set, which contains multiple relevant labels and some noisy labels. Recent studies usually solve PML problems with the disambiguation strategy, which recovers ground-truth labels from the candidate label set by simply assuming that the noisy labels are generated randomly. In real applications, however, noisy labels are usually caused by some ambiguous contents of the example. Based on this observation, we propose a partial multi-label learning approach to simultaneously recover the ground-truth information and identify the noisy labels. The two objectives are formalized in a unified framework with trace norm and$\ell_1$norm regularizers. Under the supervision of the observed noise-corrupted label matrix, the multi-label classifier and noisy label identifier are jointly optimized by incorporating the label correlation exploitation and feature-induced noise model. Furthermore, by mapping each bag to a feature vector, we extend PML-NI mehtod into multi-instance multi-label learning by identifying noisy labels based on ambiguous instances. A theoretical analysis of generalization bound and extensive experiments on multiple data sets from various real-world tasks demonstrate the effectiveness of the proposed approach.

In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise perturbations. Most existing studies assume a fixed perturbation level for all training examples, which however hardly holds in real tasks. In fact, excessive perturbations may destroy the discriminative content of an example, while deficient perturbations may fail to provide helpful information for improving the robustness. Motivated by this observation, we propose to adaptively adjust the perturbation levels for each example in the training process. Specifically, a novel active learning framework is proposed to allow the model interactively querying the correct perturbation level from human experts. By designing a cost-effective sampling strategy along with a new query type, the robustness can be significantly improved with a few queries. Both theoretical analysis and experimental studies validate the effectiveness of the proposed approach.

Active learning tries to learn an effective model with lowest labeling cost. Most existing active learning methods work in a synchronous way, which implies that the label querying can be performed only after the model updating in each iteration. While training models is usually time-consuming, it may lead to serious latency between two queries, especially in the crowdsourcing environments where there are many online annotators working simultaneously. This will significantly decrease the labeling efficiency and strongly limit the application of active learning in real tasks. To overcome this challenge, we propose a multi-server multi-worker framework for asynchronous active learning in the distributed environment. By maintaining two shared pools of candidate queries and labeled data respectively, the servers, the workers and the annotators efficiently corporate with each other without synchronization. Moreover, diverse sampling strategies from distributed workers are incorporated to select the most useful instances for model improving. Both theoretical analysis and experimental study validate the effectiveness of the proposed approach.

To learn an effective model with less training examples, existing active learning methods typically assume that there is a given target model, and try to fit it by selecting the most informative examples. However, it is less likely to determine the best target model in prior, and thus may get suboptimal performance even if the data is perfectly selected. To tackle with this practical challenge, this paper proposes a novel framework of dual active learning (DUAL) to simultaneously perform model search and data selection. Specifically, an effective method with truncated importance sampling is proposed for Combined Algorithm Selection and Hyperparameter optimization (CASH), which mitigates the model evaluation bias on the labeled data. Further, we propose an active query strategy to label the most valuable examples. The strategy on one hand favors discriminative data to help CASH search the best model, and on the other hand prefers informative examples to accelerate the convergence of winner models. Extensive experiments are conducted on 12 openML datasets. The results demonstrate the proposed method can effectively learn a superior model with less labeled examples.

In partial multi-label learning (PML) problems, each instance is partially annotated with a candidate label set, which consists of multiple relevant labels and some noisy labels. To solve PML problems, existing methods typically try to recover the ground-truth information from partial annotations based on extra assumptions on the data structures. While the assumptions hardly hold in real-world applications, the trained model may not generalize well to varied PML tasks. In this paper, we propose a novel approach for partial multi-label learning with meta disambiguation (PML-MD). Instead of relying on extra assumptions, we try to disambiguate between ground-truth and noisy labels in a meta-learning fashion. On one hand, the multi-label classifier is trained by minimizing a confidence-weighted ranking loss, which distinctively utilizes the supervised information according to the label quality; on the other hand, the confidence for each candidate label is adaptively estimated with its performance on a small validation set. To speed up the optimization, these two procedures are performed alternately with an online approximation strategy. Comprehensive experiments on multiple datasets and varied evaluation metrics validate the effectiveness of the proposed method.

Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by slightly perturbing the features of correctly labeled training examples. By formalizing this malicious attack as finding the worst-case training data within a specific $\infty$-Wasserstein ball, we show that minimizing adversarial risk on the perturbed data is equivalent to optimizing an upper bound of natural risk on the original data. This implies that adversarial training can serve as a principled defense against delusive attacks. Thus, the test accuracy decreased by delusive attacks can be largely recovered by adversarial training. To further understand the internal mechanism of the defense, we disclose that adversarial training can resist the delusive perturbations by preventing the learner from overly relying on non-robust features in a natural setting. Finally, we complement our theoretical findings with a set of experiments on popular benchmark datasets, which show that the defense withstands six different practical attacks. Both theoretical and empirical results vote for adversarial training when confronted with delusive adversaries.

Precisely annotating objects with multiple labels is costly and has become a critical bottleneck in real-world multi-label classification tasks. Instead, deciding the relative order of label pairs is obviously less laborious than collecting exact labels. However, the supervised information of pairwise relevance ordering is less informative than exact labels. It is thus an important challenge to effectively learn with such weak supervision. In this paper, we formalize this problem as a novel learning framework, called multi-label learning with pairwise relevance ordering (PRO). We show that the unbiased estimator of classification risk can be derived with a cost-sensitive loss only from PRO examples. Theoretically, we provide the estimation error bound for the proposed estimator and further prove that it is consistent with respective to the commonly used ranking loss. Empirical studies on multiple datasets and metrics validate the effectiveness of the proposed method.

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also review the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.

Label distribution learning (LDL) is proposed for solving the label ambiguity problem in recent years, which can be seen as an extension of multi-label learning. To improve the performance of label distribution learning, some existing algorithms exploit label correlations in a global manner that assumes the label correlations are shared by all instances. However, the instances in different groups may share different label correlations, and few label correlations are globally applicable in real-world tasks. In this paper, two novel label distribution learning algorithms are proposed by exploiting label correlations on local samples, which are called GD-LDL-SCL and Adam-LDL-SCL, respectively. To utilize the label correlations on local samples, the influence of local samples is encoded, and a local correlation vector is designed as the additional features for each instance, which is based on the different clustered local samples. Then, the label distribution for an unseen instance can be predicted by exploiting the original features and the additional features simultaneously. Extensive experiments on some real-world data sets validate that our proposed methods can address the label distribution problems effectively and outperform state-of-the-art methods.

Graph-based semi-supervised learning (GSSL) studies the problem where in addition to a set of data points with few available labels, there also exists a graph structure that describes the underlying relationship between data items. In practice, structure uncertainty often occurs in graphs when edges exist between data with different labels, which may further results in prediction uncertainty of labels. Considering that Gaussian process generalizes well with few labels and can naturally model uncertainty, in this paper, we propose an Uncertainty aware Graph Gaussian Process based approach (UaGGP) for GSSL. UaGGP exploits the prediction uncertainty and label smooth regularization to guide each other during learning. To further subdue the effect of irrelevant neighbors, UaGGP also aggregates the clean representation in the original space and the learned representation. Experiments on benchmarks demonstrate the effectiveness of the proposed approach.

Partial multi-label learning (PML) deals with problems where each instance is assigned with a candidate label set, which contains multiple relevant labels and some noisy labels. Recent studies usually solve PML problems with the disambiguation strategy, which recovers ground-truth labels from the candidate label set by simply assuming that the noisy labels are generated randomly. In real applications, however, noisy labels are usually caused by some ambiguous contents of the example. Based on this observation, we propose a partial multi-label learning approach to simultaneously recover the ground-truth information and identify the noisy labels. The two objectives are formalized in a unified framework with trace norm and ℓ1 norm regularizers. Under the supervision of the observed noise-corrupted label matrix, the multi-label classifier and noisy label identifier are jointly optimized by incorporating the label correlation exploitation and feature-induced noise model. Extensive experiments on synthetic as well as real-world data sets validate the effectiveness of the proposed approach.

Labeling a text document is usually time consuming because it requires the annotator to read the whole document and check its relevance with each possible class label. It thus becomes rather expensive to train an effective model for text classification when it involves a large dataset of long documents. In this paper, we propose an active learning approach for text classification with lower annotation cost. Instead of scanning all the examples in the unlabeled data pool to select the best one for query, the proposed method automatically generates the most informative examples based on the classification model, and thus can be applied to tasks with large scale or even infinite unlabeled data. Furthermore, we propose to approximate the generated example with a few summary words by sparse reconstruction, which allows the annotators to easily assign the class label by reading a few words rather than the long document. Experiments on different datasets demonstrate that the proposed approach can effectively improve the classification performance while significantly reduce the annotation cost.

Partial multi-label learning (PML) deals with problems where each instance is associated with a candidate label set, which contains multiple relevant labels and some noisy labels. In many real-world scenarios, it is impractical to annotate all examples for a huge-size dataset. Instead, a more common case is that only a small set of the data are annotated with partial labels, while most data are unlabeled. In this paper, we formalize such problems as a new learning framework called Semi-Supervised Partial Multi-label Learning (SSPML). To solve the SSPML problem, a latent label variable is introduced for each example as the low-dimensional embedding of the feature space. On one hand, label variables are recovered by encouraging consistent similarity measurement between the feature space and the label space; on the other hand, the similarities are adaptively updated based on the feedback from the label space. Meanwhile, the multi-label classifier is jointly trained under the supervision of label variables. Extensive experiments on multiple datasets from various real-world tasks validate the effectiveness of the proposed approach.

In many real tasks, we care about how to make decisions rather than mere predictions on an event, e.g. how to increase the revenue next month instead of merely knowing it will drop. The key is to identify the causal effects on the desired event. It is achievable with do-calculus if the causal structure is known; however, in many real tasks it is not easy to infer the whole causal structure with the observational data. Introducing external interventions is needed to achieve it. In this paper, we study the situation where only the response variable is observable under intervention. We propose a novel approach which is able to cost-effectively identify the causal effects, by an active strategy introducing limited interventions, and thus guide decision-making. Theoretical analysis and empirical studies validate the effectiveness of the proposed approach.

Segmenting bioimage based filaments is a critical step in a wide range of applications, including neuron reconstruction and blood vessel tracing. To achieve an acceptable segmentation performance, most of the existing methods need to annotate amounts of filamentary images in the training stage. Hence, these methods have to face the common challenge that the annotation cost is usually high. To address this problem, we propose an interactive segmentation method to actively select a few super-pixels for annotation, which can alleviate the burden of annotators. Specifically, we first apply a Simple Linear Iterative Clustering (i.e., SLIC) algorithm to segment filamentary images into compact and consistent super-pixels, and then propose a novel batch-mode based active learning method to select the most representative and informative (i.e., BMRI) super-pixels for pixel-level annotation. We then use a bagging strategy to extract several sets of pixels from the annotated super-pixels, and further use them to build different Laplacian Regularized Gaussian Mixture Models (Lap-GMM) for pixel-level segmentation. Finally, we perform the classifier ensemble by combining multiple Lap-GMM models based on a majority voting strategy. We evaluate our method on three public available filamentary image datasets. Experimental results show that, to achieve comparable performance with the existing methods, the proposed algorithm can save 40 percent annotation efforts for experts.

Open-set classification is a common problem in many real world tasks, where data is collected for known classes, and some novel classes occur at the test stage. In this paper, we focus on a more challenging case where the data examples collected for known classes are all unlabeled. Due to the high cost of label annotation, it is rather important to train a model with least labeled data for both accurate classification on known classes and effective detection of novel classes. Firstly, we propose an active learning method by incorporating structured sparsity with diversity to select representative examples for annotation. Then a latent low-rank representation is employed to simultaneously perform classification and novel class detection. Also, the method along with a fast optimization solution is extended to a multi-stage scenario, where classes occur and disappear in batches at each stage. Experimental results on multiple datasets validate the superiority of the proposed method with regard to different performance measures.

Active learning queries labels from the oracle for the most valuable instances to reduce the labeling cost. In many active learning studies, informative and representative instances are preferred because they are expected to have higher potential value for improving the model. Recently, the results in self-paced learning show that training the model with easy examples first and then gradually with harder examples can improve the performance. While informative and representative instances could be easy or hard, querying valuable but hard examples at early stage may lead to waste of labeling cost. In this paper, we propose a self-paced active learning approach to simultaneously consider the potential value and easiness of an instance, and try to train the model with least cost by querying the right thing at the right time. Experimental results show that the proposed approach is superior to state-of-the-art batch mode active learning methods.

On many video websites, the recommendation is implemented as a prediction problem of video-user pairs, where the videos are represented by text features extracted from the metadata. However, the metadata is manually annotated by users and is usually missing for online videos. To train an effective recommender system with lower annotation cost, we propose an active learning approach to fully exploit the visual view of videos, while querying as few annotations as possible from the text view. On one hand, a joint model is proposed to learn the mapping from visual view to text view by simultaneously aligning the two views and minimizing the classification loss. On the other hand, a novel strategy based on prediction inconsistency and watching frequency is proposed to actively select the most important videos for metadata querying. Experiments on both classification datasets and real video recommendation tasks validate that the proposed approach can significantly reduce the annotation cost.

Class-conditional variants of Generative adversarial networks (GANs) have recently achieved a great success due to its ability of selectively generating samples for given classes, as well as improving generation quality. However, its training requires a large set of class-labeled data, which is often expensive and difficult to collect in practice. In this paper, we propose an active sampling method to reduce the labeling cost for effectively training the class-conditional GANs. On one hand, the most useful examples are selected for external human labeling to jointly reduce the difficulty of model learning and alleviate the missing of adversarial training; on the other hand, fake examples are actively sampled for internal model retraining to enhance the adversarial training between the discriminator and generator. By incorporating the two strategies into a unified framework, we provide a cost-effective approach to train class-conditional GANs, which achieves higher generation quality with less training examples. Experiments on multiple datasets, diverse GAN configurations and various metrics demonstrate the effectiveness of our approaches.

Multi-Instance Multi-Label (MIML) learning is a popular framework in machine learning, where each object is represented by a bag of instances, and associated with multiple labels. While MIML learning has achieved success in many applications, it is less clear how the labels are related to the instances. In this paper, we propose to study the causal relation between instances and labels, which on one hand can improve the interpretability of complicated MIML models, and on the other hand may further improve the prediction performance at both instance and bag levels. We exploit prototypes in the instance space as a bridge to represent the examples, and then propose an efficient algorithm to identify the causal relations from prototypes to class labels, which are further utilized for model training and key instance detection. Experiments on various datasets show that in addition to superior classification performance, our approach can identify reasonable causal relations between instances and labels.

In many real-world tasks, particularly those involving data objects with complicated semantics such as images and texts, one object can be represented by multiple instances and simultaneously be associated with multiple labels. Such tasks can be formulated as multi-instance multi-label learning (MIML) problems, and have been extensively studied during the past few years. Existing MIML approaches have been found useful in many applications; however, most of them can only handle moderate-sized data. To efficiently handle large data sets, in this paper we propose the MIMLfast approach, which first constructs a low-dimensional subspace shared by all labels, and then trains label specific linear models to optimize approximated ranking loss via stochastic gradient descent. Although the MIML problem is complicated, MIMLfast is able to achieve excellent performance by exploiting label relations with shared space and discovering sub-concepts for complicated labels. Experiments show that the performance of MIMLfast is highly competitive to state-of-the-art techniques, whereas its time cost is much less. Moreover, our approach is able to identify the most representative instance for each label, and thus providing a chance to understand the relation between input patterns and output label semantics.

In this paper, we propose a new learning framework named dual set multi-label learning, where there are two sets of labels, and an object has one and only one positive label in each set. Compared to general multi-label learning, the exclusive relationship among labels within the same set, and the pairwise inter-set label relationship are much more explicit and more likely to be fully exploited. To handle such kind of problems, a novel boosting style algorithm with model-reuse and distribution adjusting mechanisms is proposed to make the two label sets help each other. In addition, theoretical analyses are presented to show the superiority of learning from dual label sets to learning directly from all labels. To empirically evaluate the performance of our approach, we conduct experiments on two manually collected real-world datasets along with an adapted dataset. Experimental results validate the effectiveness of our approach for dual set multi-label learning.

It is expensive and difficult to precisely annotate objects with multiple labels. Instead, in many real tasks, annotators may roughly assign each object with a set of candidate labels. The candidate set contains at least one but unknown number of ground-truth labels, and is usually adulterated with some irrelevant labels. In this paper, we formalize such problems as a new learning framework called partial multi-label learning (PML). To solve the PML problem, a confidence value is maintained for each candidate label to estimate how likely it is a ground-truth label of the instance. On one hand, the relevance ordering of labels on each instance is optimized by minimizing a rank loss weighted by the confidences; on the other hand, the confidence values are optimized by further exploiting structure information in feature and label spaces.Experimental results on various datasets show that the proposed approach is effective for solving PML problems.

Active learning reduces the labeling cost by actively querying labels for the most valuable data. It is particularly important for multi-label learning, where the annotation cost is rather high because each instance may have multiple labels simultaneously. In many multi-label tasks, the labels are organized into hierarchies from coarse to fine. The labels at different levels of the hierarchy contribute differently to the model training, and also have diverse annotation costs. In this paper, we propose a multi-label active learning approach to exploit the label hierarchies for cost-effective queries. By incorporating the potential contribution of ancestor and descendant labels, a novel criterion is proposed to estimate the informativeness of each candidate query. Further, a subset selection method is introduced to perform active batch selection by balancing the informativeness and cost of each instance-label pair. Experimental results validate the effectiveness of both the proposed criterion and the selection method.

Feature missing is a serious problem in many applications, which may lead to low quality of training data and further significantly degrade the learning performance. While feature acquisition usually involves special devices or complex process, it is expensive to acquire all feature values for the whole dataset. On the other hand, features may be correlated with each other, and some values may be recovered from the others. It is thus important to decide which features are most informative for recovering the other features as well as improving the learning performance. In this paper, we try to train an effective classification model with least acquisition cost by jointly performing active feature querying and supervised matrix completion. When completing the feature matrix, a novel objective function is proposed to simultaneously minimize the reconstruction error on observed entries and the supervised loss on training data. When querying the feature value, the most uncertain entry is actively selected based on the variance of previous iterations. In addition, a bi-objective optimization method is presented for cost-aware active selection when features bear different acquisition costs. The effectiveness of the proposed approach is well validated by both theoretical analysis and experimental study.

Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the network architecture, repeated trial-and-error process to tune the parameters, and a large set of labeled data to train the model. In this paper, we propose to overcome these challenges by actively adapting a pre-trained model to a new task with less labeled examples. Specifically, the pre-trained model is iteratively fine tuned based on the most useful examples. The examples are actively selected based on a novel criterion, which jointly estimates the potential contribution of an instance on optimizing the feature representation as well as improving the classification model for the target task. On one hand, the pre-trained model brings plentiful information from its original task, avoiding redesign of the network architecture or training from scratch; and on the other hand, the labeling cost can be significantly reduced by active label querying. Experiments on multiple datasets and different pre-trained models demonstrate that the proposed approach can achieve cost-effective training of DNNs.

The wisdom of crowds (WOCs), as a theory in the social science, gets a new paradigm in computer science. The WOC theory explains that the aggregate decision made by a group is often better than those of its individual members if specific conditions are satisfied. This paper presents a novel framework for unsupervised and semisupervised cluster ensemble by exploiting the WOC theory. We employ four conditions in the WOC theory, i.e., diversity, independency, decentralization, and aggregation, to guide both constructing of individual clustering results and final combination for clustering ensemble. First, independency criterion, as a novel mapping system on the raw data set, removes the correlation between features on our proposed method. Then, decentralization as a novel mechanism generates high quality individual clustering results. Next, uniformity as a new diversity metric evaluates the generated clustering results. Further, weighted evidence accumulation clustering method is proposed for the final aggregation without using thresholding procedure. Experimental study on varied data sets demonstrates that the proposed approach achieves superior performance to state-of-the-art methods.

In this paper, we propose a joint conditional graphical Lasso to learn multiple conditional Gaussian graphical models, also known as Gaussian conditional random fields, with some similar structures. Our model builds on the maximum likelihood method with the convex sparse group Lasso penalty. Moreover, our model is able to model multiple multivariate linear regressions with unknown noise covariances via a convex formulation. In addition, we develop an efficient approximated Newton's method for optimizing our model. Theoretically, we establish the asymptotic properties of our model on consistency and sparsistency under the high-dimensional settings. Finally, extensive numerical results on simulations and real data sets demonstrate that our method outperforms the compared methods on structure recovery and structured output prediction. To the best of our knowledge, the joint learning of multiple multivariate regressions with unknown covariance is first studied.

In traditional active learning, there is only one labeler that always returns the ground truth of queried labels. However, in many applications, multiple labelers are available to offer diverse qualities of labeling with different costs. In this paper, we perform active selection on both instances and labelers, aiming to improve the classification model most with the lowest cost. While the cost of a labeler is proportional to its overall labeling quality, we also observe that different labelers usually have diverse expertise, and thus it is likely that labelers with a low overall quality can provide accurate labels on some specific instances. Based on this fact, we propose a novel active selection criterion to evaluate the cost-effectiveness of instance-labeler pairs, which ensures that the selected instance is helpful for improving the classification model, and meanwhile the selected labeler can provide an accurate label for the instance with a relative low cost. Experiments on both UCI and real crowdsourcing data sets demonstrate the superiority of our proposed approach on selecting cost-effective queries.

Multi-instance multi-label learning(MIML) has been successfully applied into many real-world applications. Along with the enhancing of the expressive power, the cost of labelling a MIML example increases significantly. And thus it becomes an important task to train an effective MIML model with as few labelled examples as possible. Active learning, which actively selects the most valuable data to query their labels, is a main approach to reducing labeling cost. Existing active methods achieved great success in traditional learning tasks, but cannot be directly applied to MIML problems. In this paper, we propose a MIML active learning algorithm, which exploits diversity and uncertainty in both the input and output space to query the most valuable information. This algorithm designs a novel query strategy for MIML objects specifically and acquires more precise information from the oracle without addition cost. Based on the queried information, the MIML model is then effectively trained by simultaneously optimizing the relative rank among instances and labels.

Linear classifier is an essential part of machine learning, and improving its robustness has attracted much effort. Logistic regression (LR) is one of the most widely used linear classifier for its simplicity and probabilistic output. To reduce the risk of overfitting, LR was enhanced by introducing a generalized logistic loss (GLL) with a L2-norm regularization, aiming to maximize the minimum margin. However, the strategy of maximizing minimal margin is less robust to noisy data. In this paper, we incorporate GLL with margin distribution to exploit the statistical information from the training data, and propose a margin distribution logistic machine (MDLM) for better generalization performance and robustness. Furthermore, we extend MDLM to a multi-class version and learn different classes simultaneously by utilizing more information shared across these classes. Extensive experimental results validate the effectiveness of MDLM on both binary classification and multi-class classification.

In multi-instance multi-label learning (MIML), one object is represented by multiple instances and simultaneously associated with multiple labels. Existing MIML approaches have been found useful in many applications; however, most of them can only handle moderate-sized data. To efficiently handle large data sets, we propose the MIMLfast approach, which first constructs a low-dimensional subspace shared by all labels, and then trains label specific linear models to optimize approximated ranking loss via stochastic gradient descent. Although the MIML problem is complicated, MIMLfast is able to achieve excellent performance by exploiting label relations with shared space and discovering sub-concepts for complicated labels. Experiments show that the performance of MIMLfast is highly competitive to state-of-the-art techniques, whereas its time cost is much less; particularly, on a data set with 30K bags and 270K instances, where none of existing approaches can return results in 24 hours, MIMLfast takes only 12 minutes. Moreover, our approach is able to identify the most representative instance for each label, and thus providing a chance to understand the relation between input patterns and output semantics.

Active learning reduces the labeling cost by iteratively selecting the most valuable data to query their labels. It has attracted a lot of interests given the abundance of unlabeled data and the high cost of labeling. Most active learning approaches select either informative or representative unlabeled instances to query their labels, which could significantly limit their performance. Although several active learning algorithms were proposed to combine the two query selection criteria, they are usually ad hoc in finding unlabeled instances that are both informative and representative. We address this limitation by developing a principled approach, termed QUIRE, based on the min-max view of active learning. The proposed approach provides a systematic way for measuring and combining the informativeness and representativeness of an unlabeled instance. Further, by incorporating the correlation among labels, we extend the QUIRE approach to multi-label learning by actively querying instance-label pairs. Extensive experimental results show that the proposed QUIRE approach outperforms several state-of-the-art active learning approaches in both single-label and multi-label learning.

Automated annotation of protein function is challenging. As the number of sequenced genomes rapidly grows, the vast majority of proteins can only be annotated computationally. Nature often brings several domains together to form multi-domain and multi-functional proteins with a vast number of possibilities, and each domain may fulfill its own function independently or in a concerted manner with its neighbors. Thus, it is evident that the protein function prediction problem is naturally and inherently Multi-Instance Multi-Label (MIML) learning tasks. Based on the state-of-the-art MIML algorithm MIMLNN, we propose a novel ensemble MIML learning framework EnMIMLNN and design three algorithms for this task by combining the advantage of three kinds of Hausdorff distance metrics. Experiments on seven real-world organisms covering the biological three-domain system, i.e., archaea, bacteria, and eukaryote, show that the EnMIMLNN algorithms are superior to most state-of-the-art MIML and Multi-Label learning algorithms.

In multi-label learning, it is rather expensive to label instances since they are simultaneously associated with multiple labels. Therefore, active learning, which reduces the labeling cost by actively querying the labels of the most valuable data, becomes particularly important for multi-label learning. A strong multi-label active learning algorithm usually consists of two crucial elements: a reasonable criterion to evaluate the gain of queried label, and an effective classification model, based on whose prediction the criterion can be accurately computed. In this paper, we first introduce an effective multi-label classification model by combining label ranking with threshold learning, which is incrementally trained to avoid retraining from scratch after every query. Based on this model, we then propose to exploit both uncertainty and diversity in the instance space as well as the label space, and actively query the instance-label pairs which can improve the classification model most. Experimental results demonstrate the superiority of the proposed approach to state-of-the-art methods.

It is well known that exploiting label correlations is important for multi-label learning. Existing approaches typically exploit label correlations globally, by assuming that the label correlations are shared by all the instances. In real-world tasks, however, different instances may share different label correlations, and few correlations are globally applicable. In this paper, we propose the ML-LOC approach which allows label correlations to be exploited locally. To encode the local influence of label correlations, we derive a LOC code to enhance the feature representation of each instance. The global discrimination fitting and local correlation sensitivity are incorporated into a unified framework, and an alternating solution is developed for the optimization. Experimental results on a number of image, text and gene data sets validate the effectiveness of our approach.

Multi-label learning arises in many real-world tasks where an object is naturally associated with multiple concepts. It is well-accepted that, in order to achieve a good performance, the relationship among labels should be exploited. Most existing approaches require the label relationship as prior knowledge, or exploit by counting the label co-occurrence. In this paper, we propose the MAHR approach, which is able to automatically discover and exploit label relationship. Our basic idea is that, if two labels are related, the hypothesis generated for one label can be helpful for the other label. MAHR implements the idea as a boosting approach with a hypothesis reuse mechanism. In each boosting round, the base learner for a label is generated by not only learning on its own task but also reusing the hypotheses from other labels, and the amount of reuse across labels provides an estimate of the label relationship. Extensive experimental results validate that MAHR is able to achieve superior performance and discover reasonable label relationship. Moreover, we disclose that the label relationship is usually asymmetric.

Most active learning approaches select either informative or representative unlabeled instances to query their labels. Although several active learning algorithms have been proposed to combine the two criterions for query selection, they are usually ad hoc in finding unlabeled instances that are both informative and representative. We address this challenge by a principled approach, termed QUIRE, based on the min-max view of active learning. The proposed approach provides a systematic way for measuring and combining the informativeness and representativeness of an instance. Extensive experimental results show that the proposed QUIRE approach outperforms several state-of -the-art active learning approaches.