Large language models (LLMs), with their billions of parameters, pose substantial challenges for deployment on edge devices, straining both memory capacity and computational resources. Block Floating Point (BFP) quantisation reduces memory and computational overhead by converting high-overhead floating point operations into low-bit fixed point operations. However, BFP requires aligning all data to the maximum exponent, which causes loss of small and moderate values, resulting in quantisation error and degradation in the accuracy of LLMs. To address this issue, we propose a Bidirectional Block Floating Point (BBFP) data format, which reduces the probability of selecting the maximum as shared exponent, thereby reducing quantisation error. By utilizing the features in BBFP, we present a full-stack Bidirectional Block Floating Point-Based Quantisation Accelerator for LLMs (BBAL), primarily comprising a processing element array based on BBFP, paired with proposed cost-effective nonlinear computation unit. Experimental results show BBAL achieves a 22% improvement in accuracy compared to an outlier-aware accelerator at similar efficiency, and a 40% efficiency improvement over a BFP-based accelerator at similar accuracy.

The emergence of multimodal large language models (MLLMs) presents promising opportunities for automation and enhancement in Electronic Design Automation (EDA). However, comprehensively evaluating these models in circuit design remains challenging due to the narrow scope of existing benchmarks. To bridge this gap, we introduce MMCircuitEval, the first multimodal benchmark specifically designed to assess MLLM performance comprehensively across diverse EDA tasks. MMCircuitEval comprises 3614 meticulously curated question-answer (QA) pairs spanning digital and analog circuits across critical EDA stages—ranging from general knowledge and specifications to front-end and back-end design. Derived from textbooks, technical question banks, datasheets, and real-world documentation, each QA pair undergoes rigorous expert review for accuracy and relevance. Our benchmark uniquely categorizes questions by design stage, circuit type, tested abilities (knowledge, comprehension, reasoning, computation), and difficulty level, enabling detailed analysis of model capabilities and limitations. Extensive evaluations reveal significant performance gaps among existing LLMs, particularly in back-end design and complex computations, highlighting the critical need for targeted training datasets and modeling approaches. MMCircuitEval provides a foundational resource for advancing MLLMs in EDA, facilitating their integration into real-world circuit design workflows. Our benchmark is available at https://github.com/cure-lab/MMCircuitEval.

Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain using only unlabeled test samples. Most existing TTA approaches rely on definite pseudo-labels, inevitably introducing false labels and failing to capture uncertainty for each test sample. This prevents pseudo-labels from being flexibly refined as the model adapts during training, limiting their potential for performance improvement. To address this, we propose the Progressive Adaptation with Selective Label Enhancement (PASLE) framework. Instead of definite labels, PASLE assigns candidate pseudo-label sets to uncertain ones via selective label enhancement. Specifically, PASLE partitions data into confident/uncertain subsets, assigning one-hot labels to confident samples and candidate sets to uncertain ones. The model progressively trains on certain/uncertain pseudo-labeled data while dynamically refining uncertain pseudo-labels, leveraging increasing target adaptation monitored throughout training. Experiments on various benchmark datasets validate the effectiveness of the proposed approach.

Large Language Models (LLM) alignment aims to prevent models from producing content that misaligns with human expectations, which can lead to ethical and legal concerns. In the last few years, Reinforcement Learning from Human Feedback (RLHF) has been the most prominent method for achieving alignment. Due to challenges in stability and scalability with RLHF stages, which arise from the complex interactions between multiple models, researchers are exploring alternative methods to achieve effects comparable to those of RLHF. However, these methods often rely on large high-quality datasets. Despite some methods considering the generation of additional data to expand datasets, they often treat model training and data generation as separate and static processes, overlooking the fact that these processes are highly interdependent, leading to inefficient utilization of the generated data. To deal with this problem, we propose PLE, i.e., Progressively Label Enhancement for LLM Alignment, a framework that dynamically adjusts the model’s training process based on the evolving quality of the generated data. Specifically, we prompt the model to generate responses for both the original query and a set of carefully designed principle guided query, and then utilize a dynamic threshold to determine the appropriate training approach for both responses based on their corresponding reward scores. Experimental results demonstrate the effectiveness of PLE compared to existing LLM alignment methods.

Single-positive multi-label learning (SPMLL) is a weakly supervised multi-label learning problem, where each training example is annotated with only one positive label. Existing SPMLL methods typically assign pseudo-labels to unannotated labels with the assumption that prior probabilities of all classes are identical. However, the class-prior of each category may differ significantly in real-world scenarios, which makes the predictive model not perform as well as expected due to the unrealistic assumption on real-world application. To alleviate this issue, a novel framework named Crisp, i.e., Class-pRiors Induced Single-Positive multi-label learning, is proposed. Specifically, a class-priors estimator is introduced, which can estimate the class-priors that are theoretically guaranteed to converge to the ground-truth class-priors. In addition, based on the estimated class-priors, an unbiased risk estimator for classification is derived, and the corresponding risk minimizer can be guaranteed to approximately converge to the optimal risk minimizer on fully supervised data. Experimental results on ten MLL benchmark datasets demonstrate the effectiveness and superiority of our method over existing SPMLL approaches.

Instance-dependent Partial Label Learning (ID-PLL) aims to learn a multi-class predictive model given training instances annotated with candidate labels related to features, among which correct labels are hidden fixed but unknown. The previous works involve leveraging the identification capability of the training model itself to iteratively refine supervision information. However, these methods overlook a critical aspect of ID-PLL: within the original label space, the model may fail to distinguish some incorrect candidate labels that are strongly correlated with features from correct labels. This leads to poor-quality supervision signals and creates a bottleneck in the training process. In this paper, we propose to leverage reduction-based pseudo-labels to alleviate the influence of incorrect candidate labels and train our predictive model to overcome this bottleneck. Specifically, reduction-based pseudo-labels are generated by performing weighted aggregation on the outputs of a multi-branch auxiliary model, with each branch trained in a label subspace that excludes certain labels. This approach ensures that each branch explicitly avoids the disturbance of the excluded labels, allowing the pseudo-labels provided for instances troubled by these excluded labels to benefit from the unaffected branches. Theoretically, we demonstrate that reduction-based pseudo-labels exhibit greater consistency with the Bayes optimal classifier compared to pseudo-labels directly generated from the training predictive model.

Multi-view partial multi-label learning (MVPML) deals with training data where each example is represented by multiple feature vectors and associated with a set of candidate labels, only a subset of which are correct. The diverse representation biases present in different views complicate the annotation process in MVPML, leading to the inclusion of incorrect labels in the candidate label set. Existing methods typically merge features from different views to identify the correct labels in the training data without addressing the representation biases inherent in different views. In this paper, we propose a novel MVPML method called \textsc{Vadis}, which investigates view-aware representations for disambiguation and predictive model learning. Specifically, we exploit the global common representation shared by all views, aligning it with a local semantic similarity matrix to estimate ground-truth labels via a low-rank mapping matrix. Additionally, to identify incorrect labels, the view-specific inconsistent representation is recovered by leveraging the sparsity assumption. Experiments on real-world datasets validate the superiority of our approach over other state-of-the-art methods.

Multi-Label Learning (MLL) involves the task of assigning a set of relevant labels to a given instance. Recently, Label Enhancement (LE) has gained significant attention in various MLL tasks, as it allows for effective mining the implicit relative importance information of different labels. However, in existing LE-based MLL methods, the LE process is decoupled from the MLL process. Consequently, the label distribution recovered by the LE process may not be suitable for training the predictive model, thus affecting the overall learning system. In this study, we propose a novel approach named interactive Fusion Label Enhancement for Multi-Label Learning ( Flem ) that seamlessly integrates the LE process with the MLL process. Specifically, we introduce a matching and interaction mechanism comprising a novel interaction label enhancement loss and a contrastive alignment approach to prevent object mismatch. Furthermore, we present a unified label distribution loss that establishes the relationship between the recovered label distribution and the training of the predictive model. By leveraging these losses, the label distributions obtained from the LE process can be efficiently utilized for training the predictive model. Experimental results on multiple benchmark datasets demonstrate the effectiveness of the proposed method.

Multi-label few-shot learning (ML-FSL) refers to the task of tagging previously unseen images with a set of relevant labels, giving a small number of training examples. Modeling the correlations between instances and labels, formulated in the existing methods, allows us to extract more available knowledge from limited examples. However, they simply explore the instance and label correlations with a uniform importance assumption without considering the discrepancy of importance in different instances or labels, making the utilization of instance and label correlations a bottleneck for ML-FSL. To tackle the issue, we propose a unified framework named bilateral correlation reconstruction (BCR) to enable the network to effectively mine underlying instance and label correlations with varying importance information from both instance-to-label and label-to-instance perspectives. Specifically, from the instance-to-label perspective, we refine prototypes per category by reweighting each image with its specific instance-importance degree extracted from the similarity between the instance and the corresponding category. From the label-to-instance perspective, we smooth labels for each image by recovering latent label-importance with considering the integrated topology of all samples in a task. Experimental results on multiple benchmarks validate that BCR could outperform existing ML-FSL methods by large margins.

As the complexity of Integrated Circuits (ICs) rises, accurate routing and congestion prediction, crucial for identifying early design flaws, become essential to expedite circuit design and conserve resources in the lengthy physical design process. Despite the advancements in current congestion prediction methodologies, an essential aspect that has been largely overlooked is the spatial label-correlation between different grids in congestion prediction. The spatial label-correlation is a fundamental characteristic of circuit design, where the congestion status of a grid is not isolated but inherently influenced by the conditions of its neighboring grids. In order to fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, VALCE, i.e., VAriational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids. VALCE leverages variational inference techniques to estimate this weight, thereby enhancing the regression model’s performance by incorporating spatial dependencies. Experiment results validate the superior effectiveness of VALCE on the public available ISPD2011 and DAC2012 benchmarks using the superblue circuit line.

Soft pseudo-labels, generated by the softmax predictions of the trained networks, offer a probabilistic rather than binary form, and have been shown to improve the performance of deep neural networks in supervised learning. Most previous methods adopt classification loss to train a classifier as the soft-pseudo-label generator and fail to fully exploit their potential due to the misalignment with the target of soft-pseudo-label generation, aimed at capturing the knowledge in the data rather than making definitive classifications. Nevertheless, manually designing an effective objective function for a soft-pseudo-label generator is challenging, primarily because datasets typically lack ground-truth soft labels, complicating the evaluation of the soft pseudo-label accuracy. To deal with this problem, we propose a novel framework that alternately trains the predictive model and the soft-pseudo-label generator guided by a meta-network-parameterized objective function. The parameters of the objective function are optimized based on the feedback from both the performance of the predictive model and the soft-pseudo-label generator in the learning task. Additionally, the framework offers versatility across different learning tasks by allowing direct modifications to the task loss. Experiments on the benchmark datasets validate the effectiveness of the proposed framework.

Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data availability in multi-label learning (MLL) by leveraging unlabeled data to improve the model's performance. Due to the difficulty of estimating the reliable label correlation on minimal multi-labeled data, previous SSMLL methods fail to unlash the power of the correlation among multiple labels to improve the performance of the predictive model in SSMLL. To deal with this problem, we propose a novel SSMLL method named PCLP where the correlation-induced label prior is inferred to enhance the pseudo-labeling instead of dirtily estimating the correlation among labels. Specifically, we construct the correlated label prior probability distribution using structural causal model (SCM), constraining the correlations of generated pseudo-labels to conform to the prior, which can be integrated into a variational label enhancement framework optimized by both labeled and unlabeled instances in a unified manner. Theoretically, we demonstrate the accuracy of the generated pseudo-labels and guarantee the learning consistency of the proposed method. Comprehensive experiments on several benchmark datasets have validated the superiority of the proposed method.

One major challenge in weakly supervised learning is learning from inexact supervision, ranging from partial labels (PLs) with redundant information to the extreme of unlabeled data with insufficient information. While recent work has made significant strides in specific inexact supervision contexts, supervision forms typically coexist in complex combinations. This is exemplified in semi-supervised partial label learning, where PLs act as the exclusive supervision in a semi-supervised setting. Current strategies addressing combined inexact scenarios are usually composite, which can lead to incremental solutions that essentially replicate existing methods. In this paper, we propose a novel approach to uniformly tackle both label redundancy and insufficiency, derived from a mutual information-based perspective. We design a label channel that facilitates dynamic label exchange within the candidate label sets, which identifies potential true labels and filters out likely incorrect ones, thereby minimizing error accumulation. Experimental results demonstrate the superiority of our method over existing state-of-the-art PL and semi-supervised learning approaches by directly integrating them. Furthermore, our extended experiments on partial-complementary label learning underscore the flexibility of our uniform treatment in managing diverse supervision scenarios.

Learning with inaccurate supervision is often encountered in weakly supervised learning, and researchers have invested a considerable amount of time and effort in designing specialized algorithms for different forms of annotations in inaccurate supervision. In fact, different forms of these annotations share the fundamental characteristic that they all still incorporate some portion of correct labeling information. This commonality can serve as a lever, enabling the creation of a cohesive framework designed to tackle the challenges associated with various forms of annotations in learning with inaccurate supervision. In this paper, we propose a unified label refinement framework named ULAREF, i.e., a Unified LAbel REfinement Framework for learning with inaccurate supervision, which is capable of leveraging label refinement to handle inaccurate supervision. Specifically, our framework trains the predictive model with refined labels through global detection of reliability and local enhancement using an enhanced model fine-tuned by a proposed consistency loss. Also, we theoretically justify that the enhanced model in local enhancement can achieve higher accuracy than the predictive model on the detected unreliable set under mild assumptions.

A partial label (PL) specifies a set of candidate labels for an instance and partial-label learning (PLL) trains multi-class classifiers with PLs. Recently, many methods that incorporate techniques from other domains have shown strong potential. The expectation that stronger techniques would enhance performance has resulted in prominent PLL methods becoming not only highly complicated but also quite different from one another, making it challenging to choose the best direction for future algorithm design. While it is exciting to see higher performance, this leaves open a fundamental question: what makes a PLL method effective? We present a comprehensive empirical analysis of this question and summarize the success of PLL so far into some minimal algorithm design principles. Our findings reveal that high accuracy on benchmark-simulated datasets with PLs can misleadingly amplify the perceived effectiveness of some general techniques, which may improve representation learning but have limited impact on addressing the inherent challenges of PLs. We further identify the common behavior among successful PLL methods as a progressive transition from uniform to one-hot pseudo-labels, highlighting the critical role of mini-batch PL purification in achieving top performance. Based on our findings, we introduce a minimal working algorithm that is surprisingly simple yet effective, and propose an improved strategy to implement the design principles, suggesting a promising direction for improvements in PLL.

Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL). In PLL, identification-based strategy (IBS) purifies each PL on the fly to select the (most likely) TL for training; average-based strategy (ABS) treats all candidate labels equally for training and let trained models be able to predict TL. Although PLL research has focused on IBS for better performance, ABS is also worthy of study since modern IBS behaves like ABS in the beginning of training to prepare for PL purification and TL selection. In this paper, we analyze why ABS was unsatisfactory and propose how to improve it. Theoretically, we propose two problem settings of PLL and prove that average PL losses (APLLs) with bounded multi-class losses are always robust, while APLLs with unbounded losses may be non-robust, which is the first robustness analysis for PLL. Experimentally, we have two promising findings: ABS using bounded losses can match/exceed state-of-the-art performance of IBS using unbounded losses; after using robust APLLs to warm start, IBS can further improve upon itself. Our work draws attention to ABS research, which can in turn boost IBS and push forward the whole PLL.

Partial label learning (PLL) is a form of weakly supervised learning, where each training example is linked to a set of candidate labels, among which only one label is correct. Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels. However, in practice, this assumption may not hold true, as the candidate labels are often instance-dependent. In this paper, we address the instance-dependent PLL problem and assume that each example is associated with a latent label distribution where the incorrect label with a high degree is more likely to be annotated as a candidate label. Motivated by this consideration, we propose two methods VALEN and MILEN, which train the predictive model via utilizing the latent label distributions recovered by the label enhancement process. Specifically, VALEN recovers the latent label distributions via inferring the variational posterior density parameterized by an inference model with the deduced evidence lower bound. MILEN recovers the latent label distribution by adopting the variational approximation to bound the mutual information among the latent label distribution, observed labels and augmented instances. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed methods.

Multi-label text classification (MLTC) refers to the problem of tagging a given document with the most relevant subset of labels. One of the biggest challenges for MLTC is the existence of class imbalance. Most advanced MLTC models suffer from this issue, which limits the performance of the models. In this paper, we propose a model-agnostic framework named variational continuous label distribution learning (VCLDL) to address this problem. VCLDL theoretically builds a corresponding relationship between the feature space and the label space to mine the information hidden in the observable logical labels. Specifically, VCLDL regards label distribution as a continuous density function in latent space and forms a flexible variational approach to approximate the density function of the labels with the collaboration of the feature space. Combined with VCLDL, MLTC models can pay more attention to the distribution of the whole label set, rather than specific labels with maximum response values, thus the class imbalance problem can be well overcome. Experimental results on multiple benchmark datasets demonstrate that VCLDL can bring significant performance improvements over the existing MLTC models.

Label distribution covers a certain number of labels, representing the degree to which each label describes an instance. The learning process on the instances labeled by label distributions is called Label Distribution Learning (LDL). Although LDL has been applied successfully to many practical applications, one problem with existing LDL methods is that they are limited to data with balanced label information. However, annotation information in real-world data often exhibits imbalanced distributions, which significantly degrades the performance of existing methods. In this paper, we investigate the Imbalanced Label Distribution Learning (ILDL) problem. To handle this challenging problem, we delve into the characteristics of ILDL and empirically find that the representation distribution shift is the underlying reason for the performance degradation of existing methods. Inspired by this finding, we present a novel method named Representation Distribution Alignment (RDA). RDA aligns the distributions of feature representations and label representations to alleviate the impact of the distribution gap between the training set and the test set caused by the imbalance issue. Extensive experiments verify the superior performance of RDA. Our work fills the gap in benchmarks and techniques for practical ILDL problems.

Under partial-label learning (PLL) where, for each training instance, only a set of ambiguous candidate labels containing the unknown true label is accessible, contrastive learning has recently boosted the performance of PLL on vision tasks, attributed to representations learned by contrasting the same/different classes of entities. Without access to true labels, positive points are predicted using pseudolabels that are inherently noisy, and negative points often require large batches or momentum encoders, resulting in unreliable similarity information and a high computational overhead. In this paper, we rethink a state-of-the-art contrastive PLL method PiCO [24], inspiring the design of a simple framework termed PaPi (Partial-label learning with a guided Prototypical classifier), which demonstrates significant scope for improvement in representation learning, thus contributing to label disambiguation. PaPi guides the optimization of a prototypical classifier by a linear classifier with which they share the same feature encoder, thus explicitly encouraging the representation to reflect visual similarity between categories. It is also technically appealing, as PaPi requires only a few components in PiCO with the opposite direction of guidance, and directly eliminates the contrastive learning module that would introduce noise and consume computational resources. We empirically demonstrate that PaPi significantly outperforms other PLL methods on various image classification tasks.

Partial label learning (PLL) aims to train multiclass classifiers from the examples each annotated with a set of candidate labels where a fixed but unknown candidate label is correct. In the last few years, the instance-independent generation process of candidate labels has been extensively studied, on the basis of which many theoretical advances have been made in PLL. Nevertheless, the candidate labels are always instance-dependent in practice and there is no theoretical guarantee that the model trained on the instance-dependent PLL examples can converge to an ideal one. In this paper, a theoretically grounded and practically effective approach named POP, i.e. PrOgressive Purification for instance-dependent partial label learning, is proposed. Specifically, POP updates the learning model and purifies each candidate label set progressively in every epoch. Theoretically, we prove that POP enlarges the region appropriately fast where the model is reliable, and eventually approximates the Bayes optimal classifier with mild assumptions. Technically, POP is flexible with arbitrary PLL losses and could improve the performance of the previous PLL losses in the instance-dependent case. Experiments on the benchmark datasets and the real-world datasets validate the effectiveness of the proposed method.

To deal with the challenge of high cost of annotating all relevant labels for each example in multi-label learning, single-positive multi-label learning (SPMLL) has been studied in recent years, where each example is annotated with only one positive label. By adopting pseudo-label generation, i.e., assigning pseudo-label to each example by various strategies, existing methods have empirically validated that SPMLL would significantly reduce the amount of supervision with a tolerable damage in classification performance. However, there is no existing method that can provide a theoretical guarantee for learning from pseudo-label on SPMLL. In this paper, the conditions of the effectiveness of learning from pseudo-label for SPMLL are shown and the learnability of pseudo-label-based methods is proven. Furthermore, based on the theoretical guarantee of pseudo-label for SPMLL, we propose a novel SPMLL method named MIME, i.e., Mutual label enhancement for sIngle-positive Multi-label lEarning and prove that the generated pseudo-label by MIME approximately converges to the fully-supervised case. Experiments on four image datasets and five MLL datasets show the effectiveness of our methods over several existing SPMLL approaches.

To reduce the difficulty of annotation, partial label learning (PLL) has been widely studied, where each example is ambiguously annotated with a set of candidate labels instead of the exact correct label. PLL assumes that the candidate label set contains the correct label, which induces disambiguation, i.e., identification of the correct label in the candidate label set, adopted in most PLL methods. However, this assumption is impractical as no one could guarantee the existence of the correct label in the candidate label set under real-world scenarios. Therefore, Unreliable Partial Label Learning (UPLL) is investigated where the correct label of each example may not exist in the candidate label set. In this paper, we propose a fusion framework of refinement and disambiguation named FREDIS to handle the UPLL problem. Specifically, with theoretical guarantees, not only does disambiguation move incorrect labels from candidate labels to non-candidate labels but also refinement, an opposite procedure, moves correct labels from non-candidate labels to candidate labels. Besides, we prove that the classifier trained by our framework could eventually approximate the Bayes optimal classifier. Extensive experiments on widely used benchmark datasets validate the effectiveness of our proposed framework.

Partial label learning (PLL) is a typical weakly supervised learning problem in which each instance is associated with a candidate label set, and among which only one is true. However, the assumption that the ground-truth label is always among the candidate label set would be unrealistic, as the reliability of the candidate label sets in real-world applications cannot be guaranteed by annotators. Therefore, a generalized PLL named Unreliable Partial Label Learning (UPLL) is proposed, in which the true label may not be in the candidate label set. Due to the challenges posed by unreliable labeling, previous PLL methods will experience a marked decline in performance when applied to UPLL. To address the issue, we propose a two-stage framework named Unreliable Partial Label Learning with Recursive Separation (UPLLRS). In the first stage, the self-adaptive recursive separation strategy is proposed to separate the training set into a reliable subset and an unreliable subset. In the second stage, a disambiguation strategy is employed to progressively identify the ground-truth labels in the reliable subset. Simultaneously, semi-supervised learning methods are adopted to extract valuable information from the unreliable subset. Our method demonstrates state-of-the-art performance as evidenced by experimental results, particularly in situations of high unreliability. Code and supplementary materials are available at https://github.com/dhiyu/UPLLRS.

Since the advent of knowledge distillation, many researchers have been intrigued by the $\textit{dark knowledge}$ hidden in the soft labels generated by the teacher model. This prompts us to scrutinize the circumstances under which these soft labels are effective. Predominant existing theories implicitly require that the soft labels are close to the ground-truth labels. In this paper, however, we investigate whether biased soft labels are still effective. Here, bias refers to the discrepancy between the soft labels and the ground-truth labels. We present two indicators to measure the effectiveness of the soft labels. Based on the two indicators, we propose moderate conditions to ensure that, the biased soft label learning problem is both $\textit{classifier-consistent}$ and $\textit{Empirical Risk Minimization}$ (ERM) $\textit{learnable}$, which can be applicable even for large-biased soft labels. We further design a heuristic method to train Skillful but Bad Teachers (SBTs), and these teachers with accuracy less than 30\% can teach students to achieve accuracy over 90\% on CIFAR-10, which is comparable to models trained on the original data. The proposed indicators adequately measure the effectiveness of the soft labels generated in this process. Moreover, our theoretical framework can be adapted to elucidate the effectiveness of soft labels in three weakly-supervised learning paradigms, namely incomplete supervision, partial label learning and learning with additive noise. Experimental results demonstrate that our indicators can measure the effectiveness of biased soft labels generated by teachers or in these weakly-supervised learning paradigms.

Multi-label learning focuses on the ambiguity at the label side, i.e., one instance is associated with multiple class labels, where the logical labels are always adopted to partition class labels into relevant labels and irrelevant labels rigidly. However, the relevance or irrelevance of each label corresponding to one instance is essentially relative in real-world tasks and the label distribution is more fine-grained than the logical labels by denoting one instance with a certain number of the description degrees of all class labels. As the label distribution is not explicitly available in most training sets, a process named label enhancement emerges to recover the label distributions in training datasets. By inducing the generative model of the label distribution and adopting the variational inference technique, the approximate posterior density of the label distributions should maximize the variational lower bound. Following the above consideration, LEVI is proposed to recover the label distributions from the training examples. In addition, the multi-label predictive model is induced for multi-label learning by leveraging the recovered label distributions along with a specialized objective function. The recovery experiments on fourteen label distribution datasets and the predictive experiments on fourteen multi-label learning datasets validate the advantage of our approach over the state-of-the-art approaches.

Label Distribution Learning (LDL) has attracted increasing research attentions due to its potential to address the label ambiguity problem in machine learning and success in many real-world applications. In LDL, it is usually expensive to obtain the ground-truth label distributions of data, but it is relatively easy to obtain the logical labels of data. How to use training instances only with logical labels to learn an effective LDL model is a challenging problem. In this paper, we propose a two-step framework to address this problem. Specifically, we firstly design an efficient recovery model to recover the latent label distributions of training instances, named Fast Label Enhancement (FLE). Our idea is to use non-negative matrix factorization (NMF) to mine the label distribution information from the feature space. Moreover, we take the instance-class similarities into consideration to discover the importance of each label to training instances, which is useful for learning precise label distributions. Then, we train a predictive model for testing instances based on generated label distributions of training instances and an existing LDL method (e.g., SA-BFGS). Experimental results on fifteen benchmark datasets show the effectiveness of the proposed two-step framework and verify the superiority of FLE over several state-of-the-art approaches.

Multi-view partial multi-label learning (MVPML) aims to learn a multi-label predictive model from the training examples, each of which is presented by multiple feature vectors while associated with a set of candidate labels where only a subset is correct. Generally, existing techniques work simply by identifying the ground-truth label via aggregating the features from all views to train a final classifier, but ignore the cause of the incorrect labels in the candidate label sets, i.e., the diverse property of the representation from different views leads to the incorrect labels which form the candidate labels alone with the essential supervision. In this paper, a novel MVPML approach is proposed to learn the predictive model and the incorrect-labeling model jointly by incorporating the graph-fusion-based topological structure of the feature space. Specifically, the latent label distribution and the incorrect labels are identified simultaneously in a unified framework under the supervision of candidate labels. In addition, a common topological structure of the feature space from all views is learned via the graph fusion for further capturing the latent label distribution. Experimental results on the real-world datasets clearly validate the effectiveness of the proposed approach for solving multi-view partial multi-label learning problems.

Label distribution covers a certain number of labels, representing the degree to which each label describes the instance. Label enhancement (LE) is a procedure of recovering the label distribution from the logical labels in the training data, the purpose of which is to better depict the label ambiguity through label distribution. However, data annotation inevitably introduces label noise, and it is extremely challenging to implement LE on corrupted labels. To deal with this problem, one way to recover the label distribution from the corrupted labels is to be guided by a small batch of trusted data. In this article, a novel LE method named TALEN is proposed via recovering and progressively refining label distribution guided by trusted data. Specifically, an LE process is applied to the untrusted data to select samples with a clean label. In addition, a combined loss function is designed to train the predictive model for classification. Experiments on datasets with synthetic label noise validate the feasibility of identifying clean labels via the recovered label distribution. Furthermore, experimental results on both synthetic label noise and real-world label noise on image datasets and additional experiments on text datasets show a clear advantage of TALEN over several existing noise-robust learning methods.

Partial multi-label learning (PML) aims to learn a multilabel predictive model from the PML training examples, each of which is associated with a set of candidate labels where only a subset is valid. The common strategy to induce a predictive model is identifying the valid labels in each candidate label set. Nonetheless, this strategy ignores considering the essential label distribution corresponding to each instance as label distributions are not explicitly available in the training dataset. In this article, a novel partial multilabel learning method is proposed to recover the latent label distribution and progressively enhance it for predictive model induction. Specifically, the label distribution is recovered by considering the observation model for logical labels and the sharing topological structure from feature space to label distribution space. Besides, the latent label distribution is progressively enhanced by recovering latent labeling information and supervising predictive model training alternatively to make the label distribution appropriate for the induced predictive model. Experimental results on PML datasets clearly validate the effectiveness of the proposed method for solving partial multilabel learning problems. In addition, further experiments show the high quality of the recovered label distributions and the effectiveness of adopting label distributions for partial multilabel learning.

Although deep learning has made significant progress on fixed large-scale datasets, it typically encounters challenges regarding improperly detecting unknown/unseen classes in the open-world scenario, over-parametrized, and overfitting small samples. Since biological systems can overcome the above difficulties very well, individuals inherit an innate gene from collective creatures that have evolved over hundreds of millions of years and then learn new skills through few examples. Inspired by this, we propose a practical collective-individual paradigm where an evolution (expandable) network is trained on sequential tasks and then recognize unknown classes in real-world. Moreover, the learngene, i.e., the gene for learning initialization rules of the target model, is proposed to inherit the meta-knowledge from the collective model and reconstruct a lightweight individual model on the target task. Particularly, a novel criterion is proposed to discover learngene in the collective model, according to the gradient information. Finally, the individual model is trained only with few samples on the target learning tasks. We demonstrate the effectiveness of our approach in an extensive empirical study and theoretical analysis.

Multi-label learning (MLL) refers to the problem of tagging a given instance with a set of relevant labels. In MLL, the implicit relative importance of different labels representing a single instance is generally different, which recently gained considerable attention and should be fully leveraged. Therefore, label enhancement (LE) has been widely applied in various MLL tasks as the ability to effectively mine the implicit relative importance information of different labels. However, due to the fact that the label enhancement process in previous LE-based MLL methods is decoupled from the training process on the predictive models, the objective of LE does not match the training process and finally affects the whole learning system. In this paper, we propose a novel approach named Fusion Label Enhancement for Multi-label learning (FLEM) to effectively integrate the LE process and the training process. Specifically, we design a matching and interaction mechanism which leverages a novel interaction label enhancement loss to avoid that the recovered label distribution does not match the need of the predictive model. In the meantime, we present a unified label distribution loss for establishing the corresponding relationship between the recovered label distribution and the training of the predictive model. With the proposed loss, the label distributions recovered from the LE process can be efficiently utilized for training the predictive model. Experimental results on multiple benchmark datasets validate the effectiveness of the proposed approach.

Partial label learning (PLL) learns from a typical weak supervision, where each training instance is labeled with a set of ambiguous candidate labels (CLs) instead of its exact ground-truth label. Most existing PLL works directly eliminate, rather than exploiting the label ambiguity, since they explicitly or implicitly assume that incorrect CLs are noise independent of the instance. While a more practical setting in the wild should be instance-dependent, namely, the CLs depend on both the true label and the instance itself, such that each CL may describe the instance from some sensory channel, thereby providing some noisy but really valid information about the instance. In this paper, we leverage such additional information acquired from the ambiguity and propose AmBiguity-induced contrastive LEarning (ABLE) under the framework of contrastive learning. Specifically, for each CL of an anchor, we select a group of samples currently predicted as that class as ambiguity-induced positives, based on which we synchronously learn a representor (RP) that minimizes the weighted sum of contrastive losses of all groups and a classifier (CS) that minimizes a classification loss. Although they are circularly dependent: RP requires the ambiguity-induced positives on-the-fly induced by CS, and CS needs the first half of RP as the representation extractor, ABLE still enables RP and CS to be trained simultaneously within a coherent framework. Experiments on benchmark datasets demonstrate its substantial improvements over state-of-the-art methods for learning from the instance-dependent partially labeled data.

Multi-label learning (MLL) learns from the examples each associated with multiple labels simultaneously, where the high cost of annotating all relevant labels for each training example is challenging for real-world applications. To cope with the challenge, we investigate single-positive multi-label learning (SPMLL) where each example is annotated with only one relevant label and show that one can successfully learn a theoretically grounded multi-label classifier for the problem. In this paper, a novel SPMLL method named SMILE, i.e., Single-positive MultI-label learning with Label Enhancement, is proposed. Specifically, an unbiased risk estimator is derived, which could be guaranteed to approximately converge to the optimal risk minimizer of fully supervised learning and shows that one positive label of each instance is sufficient to train the predictive model. Then, the corresponding empirical risk estimator is established via recovering the latent soft label as a label enhancement process, where the posterior density of the latent soft labels is approximate to the variational Beta density parameterized by an inference model. Experiments on benchmark datasets validate the effectiveness of the proposed method.

Reinforcement learning maps from perceived state representation to actions, which is adopted to solve the video summarization problem. The reward is crucial for deal with the video summarization task via reinforcement learning, since the reward signal defines the goal of video summarization. However, existing reward mechanism in reinforcement learning cannot handle the ambiguity which appears frequently in video summarization, i.e., the diverse consciousness by different people on the same video. To solve this problem, in this paper label distributions are mapped from the CNN and LSTM-based state representation to capture the subjectiveness of video summaries. The dual-reward is designed by measuring the similarity between user score distributions and the generated label distributions. Not only the average score but also the the variance of the subjective opinions are considered in summary generation. Experimental results on several benchmark datasets show that our proposed method outperforms other approaches under various settings.

Partial label learning (PLL) is a typical weakly supervised learning problem, where each training example is associated with a set of candidate labels among which only one is true. Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels. However, this assumption is not realistic since the candidate labels are always instance-dependent. In this paper, we consider instance-dependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature. The incorrect label with a high degree is more likely to be annotated as the candidate label. Therefore, the latent label distribution is the essential labeling information in partially labeled examples and worth being leveraged for predictive model training. Motivated by this consideration, we propose a novel PLL method that recovers the label distribution as a label enhancement (LE) process and trains the predictive model iteratively in every epoch. Specifically, we assume the true posterior density of the latent label distribution takes on the variational approximate Dirichlet density parameterized by an inference model. Then the evidence lower bound is deduced for optimizing the inference model and the label distributions generated from the variational posterior are utilized for training the predictive model. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed method. Source code is available at https://github.com/palm-ml/valen.

Label distribution is more general than both single-label annotation and multi-label annotation. It covers a certain number of labels, representing the degree to which each label describes the instance. The learning process on the instances labeled by label distributions is called label distribution learning (LDL). Unfortunately, many training sets only contain simple logical labels rather than label distributions due to the difficulty of obtaining the label distributions directly. To solve this problem, one way is to recover the label distributions from the logical labels in the training set via leveraging the topological information of the feature space and the correlation among the labels. Such process of recovering label distributions from logical labels is defined as label enhancement (LE), which reinforces the supervision information in the training sets. This paper proposes a novel LE algorithm called Graph Laplacian Label Enhancement (GLLE). Experimental results on one artificial dataset and fourteen real-world LDL datasets show clear advantages of GLLE over several existing LE algorithms. Furthermore, experimental results on eleven multi-label learning datasets validate the advantage of GLLE over the state-of-the-art multi-label learning approaches.

Partial multi-label learning (PML) aims to learn from training examples each associated with a set of candidate labels, among which only a subset are valid for the training example. The common strategy to induce predictive model is trying to disambiguate the candidate label set, such as identifying the ground-truth label via utilizing the confidence of each candidate label or estimating the noisy labels in the candidate label sets. Nonetheless, these strategies ignore considering the essential label distribution corresponding to each instance since the label distribution is not explicitly available in the training set. In this paper, a new partial multi-label learning strategy named Pml-ld is proposed to learn from partial multi-label examples via label enhancement. Specifically, label distributions are recovered by leveraging the topological information of the feature space and the correlations among the labels. After that, a multi-class predictive model is learned by fitting a regularized multi-output regressor with the recovered label distributions. Experimental results on synthetic as well as real-world datasets clearly validate the effectiveness of Pml-ld for solving PML problems.

Label distribution covers a certain number of labels, representing the degree to which each label describes the instance. When dealing with label ambiguity, label distribution could describe the supervised information in a fine-grained way. Unfortunately, many training sets only contain simple logical labels rather than label distributions due to the difficulty of obtaining label distributions directly. To solve this problem, we consider the label distributions as the latent vectors and infer them from the logical labels in the training datasets by using variational inference. After that, we induce a predictive model to train the label distribution data by employing the multi-output regression technique. The recovery experiment on thirteen real-world LDL datasets and the predictive experiment on ten multi-label learning datasets validate the advantage of our approach over the state-of-the-art approaches.

The performances of deep neural networks (DNNs) crucially rely on the quality of labeling. In some situations, labels are easily corrupted, and therefore some labels become noisy labels. Thus, designing algorithms that deal with noisy labels is of great importance for learning robust DNNs. However, it is difficult to distinguish between clean labels and noisy labels, which becomes the bottleneck of many methods. To address the problem, this paper proposes a novel method named Label Distribution based Confidence Estimation (LDCE). LDCE estimates the confidence of the observed labels based on label distribution. Then, the boundary between clean labels and noisy labels becomes clear according to confidence scores. To verify the effectiveness of the method, LDCE is combined with the existing learning algorithm to train robust DNNs. Experiments on both synthetic and real-world datasets substantiate the superiority of the proposed algorithm against state-of-the-art methods.

Partial label learning aims to learn from training examples each associated with a set of candidate labels, among which only one label is valid for the training example. The common strategy to induce predictive model is trying to disambiguate the candidate label set, such as disambiguation by identifying the ground-truth label iteratively or disambiguation by treating each candidate label equally. Nonetheless, these strategies ignore considering the generalized label distribution corresponding to each instance since the generalized label distribution is not explicitly available in the training set. In this paper, a new partial label learning strategy named PL-LE is proposed to learn from partial label examples via label enhancement. Specifically, the generalized label distributions are recovered by leveraging the topological information of the feature space. After that, a multi-class predictive model is learned by fitting a regularized multi-output regressor with the generalized label distributions. Extensive experiments show that PL-LE performs favorably against state-ofthe-art partial label learning approaches.

Weakly supervised multi-label learning (WSML) concentrates on a more challenging multi-label classification problem, where some labels in the training set are missing. Existing approaches make multi-label prediction by exploiting the incomplete logical labels directly without considering the relative importance of each label to an instance. In this paper, a novel two-stage strategy named Weakly Supervised Multi-label Learning via Label Enhancement (WSMLLE) is proposed to learn from weakly supervised data via label enhancement. Firstly, the relative importance of each label, i.e., the description degrees are recovered by leveraging the structural information in the feature space and local correlations learned from the label space. Then, a tailored multi-label predictive model is induced by learning from the training instances with the recovered description degrees. To our best knowledge, it is the first attempt to unify the complement of the missing labels and the recovery of the description degrees into the same framework. Extensive experiments across a wide range of real-world datasets clearly validate the superiority of the proposed approach.

The task of multi-label learning is to predict a set of relevant labels for the unseen instance. Traditional multi-label learning algorithms treat each class label as a logical indicator of whether the corresponding label is relevant or irrelevant to the instance, i.e., +1 represents relevant to the instance and -1 represents irrelevant to the instance. Such label represented by -1 or +1 is called logical label. Logical label cannot reflect different label importance. However, for real-world multi-label learning problems, the importance of each possible label is generally different. For the real applications, it is difficult to obtain the label importance information directly. Thus we need a method to reconstruct the essential label importance from the logical multilabel data. To solve this problem, we assume that each multi-label instance is described by a vector of latent real-valued labels, which can reflect the importance of the corresponding labels. Such label is called numerical label. The process of reconstructing the numerical labels from the logical multi-label data via utilizing the logical label information and the topological structure in the feature space is called Label Enhancement. In this paper, we propose a novel multi-label learning framework called LEMLL, i.e., Label Enhanced Multi-Label Learning, which incorporates regression of the numerical labels and label enhancement into a unified framework. Extensive comparative studies validate that the performance of multi-label learning can be improved significantly with label enhancement and LEMLL can effectively reconstruct latent label importance information from logical multi-label data.

Label distribution is more general than both single-label annotation and multi-label annotation. It covers a certain number of labels, representing the degree to which each label describes the instance. The learning process on the instances labeled by label distributions is called label distribution learning (LDL). Unfortunately, many training sets only contain simple logical labels rather than label distributions due to the difficulty of obtaining the label distributions directly. To solve the problem, one way is to recover the label distributions from the logical labels in the training set via leveraging the topological information of the feature space and the correlation among the labels. Such process of recovering label distributions from logical labels is defined as label enhancement (LE), which reinforces the supervision information in the training sets. This paper proposes a novel LE algorithm called Graph Laplacian Label Enhancement (GLLE). Experimental results on one artificial dataset and fourteen real-world datasets show clear advantages of GLLE over several existing LE algorithms.