Biological intelligence has driven significant progress in artificial intelligence (AI), but a critical gap remains: biological systems inherit innate abilities from genes, with brains initialized by blueprints refined over 3.5 billion years of evolution, while machines rely heavily on inefficient, data-driven learning from scratch. This gap arises from the lack of a genetic mechanism in machines to transfer and accumulate inheritable knowledge across generations. To bridge this gap, we propose learngenes, network fragments that act as inheritable 'genes' for machines. Unlike conventional knowledge transfer methods, learngenes enable efficient and universal knowledge transfer by selectively encapsulating task-agnostic knowledge. To facilitate the transfer and accumulation of task-agnostic knowledge across generations, we introduce Genetic Reinforcement Learning (GRL), a framework that simulates the learning and evolution of organisms in intelligent agents following Lamarckian principles. Through GRL, we identify learngenes as network fragments within agents' policy networks, equipping newborn agents with innate abilities for rapid adaptation to novel tasks. We demonstrate the advantages of learngene-based knowledge transfer over evolution-based search and traditional pre-trained models, and show how learngenes evolve through the accumulation of task-agnostic knowledge. Overall, this work establishes a novel paradigm for knowledge transfer and model initialization in AI, offering new possibilities for more adaptive, efficient, and scalable learning systems.

Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial control. However, existing methods either train separate models for each condition or rely on unified architectures with entangled representations, resulting in poor generalization and high adaptation costs for novel conditions. To this end, we propose DivControl, a decomposable pretraining framework for unified controllable generation and efficient adaptation. DivControl factorizes ControlNet via SVD into basic components—pairs of singular vectors—which are disentangled into condition-agnostic learngenes and condition-specific tailors through knowledge diversion during multi-condition training. Knowledge diversion is implemented via a dynamic gate that performs soft routing over tailors based on the semantics of condition instructions, enabling zero-shot generalization and parameter-efficient adaptation to novel conditions. To further improve condition fidelity and training efficiency, we introduce a representation alignment loss that aligns condition embeddings with early diffusion features. Extensive experiments demonstrate that DivControl achieves state-of-the-art controllability with 36.4× less training cost, while simultaneously improving average performance on basic conditions. It also delivers strong zero-shot and few-shot performance on unseen conditions, demonstrating superior scalability, modularity, and transferability.

The emergence of Intent-based Networking(IBN)-enabled Healthcare Internet of Things (H-IoT) environments brings new challenges and opportunities for deploying intelligent medical image compression systems in real-time and privacy-sensitive scenarios. However, most existing medical image compression approaches are manually designed and optimized without accounting for the high dimensionality of medical data and the strict deployment constraints in heterogeneous IBN environments, resulting in suboptimal performance and limited adaptability. To address these challenges, we propose a novel implicit neural representation (INR)-based framework for automated medical image compression, leveraging the powerful continuous signal modeling capabilities of INRs to achieve high fidelity on high-dimensional medical images while maintaining compactness and adaptability. Our framework integrates an evolutionary architecture search strategy with privacy-constrained optimization and parameter quantization, enabling the architectures that balance reconstruction quality, latency, communication cost, and privacy. To validate the effectiveness of the framework, we design and conduct comprehensive simulation experiments in realistic multi-hospital IBN environments. The results demonstrate that our INR-based designs outperform traditional and data-driven baselines in both objective metrics and deployment feasibility under constrained resources.

Smart 6G-enabled Health Internet of Things (6G-HIoT) systems represent the next generation of autonomous healthcare monitoring, leveraging ultra-reliable low-latency communications, massive machine-type connectivity, and intelligent edge computing to enable real-time health analytics across distributed medical environments. However, meeting data privacy requirements and having an effective system still needs to be solved. Existing methods need to improve on data imbalance and data distribution discrepancies across monitoring devices, making the vision of privacy-enhanced health monitoring systems unattainable. This article proposes BHMFL, an autonomous federated learning framework that addresses the challenges through scaling or balancing a certain dataset in smart 6G-HIoT systems. The framework proposes new health data formation cognate to the frequency of occurrence of different disease states through combined condition-balanced sampling and privacy data-generating technology able to keep data provided from breach. This ensures that while monitoring devices enhance the automatic representation of rare health conditions, the privacy of the devices is maintained. The framework utilizes an intelligent approach to model training that accounts for physiological and time relevance factors. Experiment results demonstrate the high performance of the proposed BHMFL framework in terms of accuracy. Additionally, the BHMFL framework has increased rare condition representation from less than 5% to around 20% without fracturing the performance across different dimensionality. These results support the intuition that BHMFL has the potential to solve the scalability and security problems of distributed health monitoring autonomously and thus can be considered beneficial for future smart 6G-HIoT systems.

Evidence prediction is the cornerstone of litigation, which requires complex legal reasoning to bridge the gap between facts and the parties’ assertions. However, most existing large language model (LLM) benchmarks do not offer a systematic assessment for evidence planning. Therefore, we introduce CLER, a large-scale Chinese Litigation Evidence Reasoning benchmark. CLER is built through a four-stage pipeline from millions of real civil and criminal judgments. The pipeline includes (1) semi-structured data collection, (2) LLM-based evidence extraction, (3) purpose refinement through decomposition into legal elements, and (4) validation through a tri-party adversarial review method that imitates courtroom debate. To this end, we obtain over 100,000 samples and conduct extensive experiments on 23 baselines, including open-weight, commercial, domain-specific LLMs and retrieval-augmented generation (RAG) systems. The findings indicate that the task poses a major challenge for current LLMs. RAG strategies, particularly a hybrid method retrieving similar cases, achieve the best performance with an F1 score of 54.4%, surpassing state-of-the-art proprietary models and improving the base model by at least 22%. Our analysis reveals several key insights. There is a significant performance gap with an average difference F1 of 16.2% exists between element checking in civil cases and narrative completeness in criminal cases. There is an inverted U-shaped correlation between case length and model performance, as insufficient or overloaded information leads to abandonment of precise reasoning, causing an average drop of approximately 10% in F1.

Label Distribution Learning (LDL) is a novel machine learning paradigm that addresses the problem of label ambiguity and has found widespread applications. However, obtaining complete label distributions in real-world scenarios is challenging, which has led to the emergence of Incomplete Label Distribution Learning (InLDL). Existing InLDL methods attempt to utilize low-rank label correlations to recover the complete label distribution. However, we find that real-world LDL datasets have animbalancednature; that is, the sum of the description degrees for normal labels is significantly larger than that for tail labels, which disrupts the low-rank assumption underlying the recovery of the label distribution. To solve the above problem, we propose Incomplete and Imbalance Label Distribution Learning (I2LDL), which makes the use of low-rank label correlations more reasonable for InLDL. Our method decomposes the recovered label distribution matrix into a low-rank component for frequent labels and a sparse component for tail labels, effectively capturing the structure of both head and tail labels. We further require that the entries in the observed positions of the recovered label distribution matrix be close to the observed values, and that the recovered label distribution for every instance forms a probability simplex (i.e., nonnegative entries summing to unity). Finally, the proposed model is optimized via the Alternating Direction Method of Multipliers (ADMM). We provide a theoretical analysis of its exact recovery guarantee under standard assumptions of incoherence, sparsity, and sufficient sampling. Furthermore, we establish a generalization error bound based on Rademacher complexity, offering theoretical insights into the learning performance of our method. Extensive experiments on 16 real-world datasets demonstrate the effectiveness and robustness of our framework compared to existing InLDL methods. The code is available at https://anonymous.4open.science/r/IncomLDL-tailaware-C021.

The growing complexity of model parameters underscores the significance of pre-trained models. However, deployment constraints often necessitate models of varying sizes, exposing limitations in the conventional pre-training and fine-tuning paradigm, particularly when target model sizes are incompatible with pre-trained ones. To address this challenge, we propose WAVE, a novel approach that reformulates variable-sized model initialization from a multitask perspective, where initializing each model size is treated as a distinct task. WAVE employs shared, size-agnostic weight templates alongside size-specific weight scalers to achieve consistent initialization across various model sizes. These weight templates, constructed within the Learngene framework, integrate knowledge from pre-trained models through a distillation process constrained by Kronecker-based rules. Target models are then initialized by concatenating and weighting these templates, with adaptive connection rules established by lightweight weight scalers, whose parameters are learned from minimal training data. Extensive experiments demonstrate the efficiency of WAVE, achieving state-of-the-art performance in initializing models of various depth and width. The knowledge encapsulated in weight templates is also task-agnostic, allowing for seamless transfer across diverse downstream datasets. Code will be made available at https://github.com/fu-feng/WAVE.

"Creative" remains an inherently abstract concept for both humans and diffusion models. While text-to-image (T2I) diffusion models can easily generate out-of-distribution concepts like "a blue banana", they struggle with generating combinatorial objects such as "a creative mixture that resembles a lettuce and a mantis", due to difficulties in understanding the semantic depth of "creative". Current methods rely heavily on synthesizing reference prompts or images to achieve a creative effect, typically requiring retraining for each unique creative output—a process that is computationally intensive and limits practical applications. To address this, we introduce CreTok, which brings meta-creativity to diffusion models by redefining "creative" as a new token,, thus enhancing models’ semantic understanding for combinatorial creativity. CreTok achieves such redefinition by iteratively sampling diverse text pairs from our proposed CangJie dataset to form adaptive prompts and restrictive prompts, and then optimizing the similarity between their respective text embeddings. Extensive experiments demonstrate thatenables the universal and direct generation of combinatorial creativity across diverse concepts without additional training, achieving state-of-the-art performance with improved text-image alignment and higher human preference ratings. Code will be made available at https://github.com/fu-feng/CreTok.

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.

Deep Neural Networks are increasingly leveraging sparsity to reduce the scaling up of model parameter size. However, reducing wall-clock time through sparsity and pruning remains challenging due to irregular memory access patterns, leading to frequent cache misses. In this paper, we present NPU Vector Runahead (NVR), a prefetching mechanism tailored for NPUs to address cache miss problems in sparse DNN workloads. Rather than optimising memory patterns with high overhead and poor portability, NVR adapts runahead execution to the unique architecture of NPUs. NVR provides a general micro-architectural solution for sparse DNN workloads without requiring compiler or algorithmic support, operating as a decoupled, speculative, lightweight hardware sub-thread alongside the NPU, with minimal hardware overhead (under 5%). NVR achieves an average 90% reduction in cache misses compared to SOTA prefetching in general-purpose processors, delivering 4 x average speedup on sparse workloads versus NPUs without prefetching. Moreover, we investigate the advantages of incorporating a small cache (16 KB) into the NPU combined with NVR. Our evaluation shows that expanding this modest cache delivers 5x higher performance benefits than increasing the $\mathbf{L 2}$ cache size by the same amount.

Pre-trained models have become the preferred backbone due to the increasing complexity of model parameters. However, traditional pre-trained models often face deployment challenges due to their fixed sizes, and are prone to negative transfer when discrepancies arise between training tasks and target tasks. To address this, we propose **KIND**, a novel pre-training method designed to construct decomposable models. KIND integrates knowledge by incorporating Singular Value Decomposition (SVD) as a structural constraint, with each basic component represented as a combination of a column vector, singular value, and row vector from $U$, $\Sigma$, and $V^\top$ matrices. These components are categorized into **learngenes** for encapsulating class-agnostic knowledge and \textbf{tailors} for capturing class-specific knowledge, with knowledge diversion facilitated by a class gate mechanism during training. Extensive experiments demonstrate that models pre-trained with KIND can be decomposed into learngenes and tailors, which can be adaptively recombined for diverse resource-constrained deployments. Moreover, for tasks with large domain shifts, transferring only learngenes with task-agnostic knowledge, when combined with randomly initialized tailors, effectively mitigates domain shifts. Code will be made available at https://github.com/Te4P0t/KIND.

Multi-label learning (MLL) has gained attention for its ability to represent real-world data. Label Distribution Learning (LDL), an extension of MLL to learning from label distributions, faces challenges in collecting accurate label distributions. To address the issue of biased annotations, based on the low-rank assumption, existing works recover true distributions from biased observations by exploring the label correlations. However, recent evidence shows that the label distribution tends to be full-rank, and naive apply of low-rank approximation on biased observation leads to inaccurate recovery and performance degradation. In this paper, we address the LDL with biased annotations problem from a novel perspective, where we first degenerate the soft label distribution into a hard multi-hot label and then recover the true label information for each instance. This idea stems from an insight that assigning hard multi-hot labels is often easier than assigning a soft label distribution, and it shows stronger immunity to noise disturbances, leading to smaller label bias. Moreover, assuming that the multi-label space for predicting label distributions is low-rank offers a more reasonable approach to capturing label correlations. Theoretical analysis and experiments confirm the effectiveness and robustness of our method on real-world datasets.

Knowledge in modern neural networks is often entangled and structurally opaque, making current transfer methods—typically based on reusing entire parameter sets—inefficient and inflexible. Efforts to improve flexibility by reusing partial parameters frequently depend on handcrafted heuristics or rigid structural assumptions, which constrain generalization. In contrast, biological evolution enables efficient knowledge transfer by encoding only essential information into genes through iterative refinement under environmental pressure. Inspired by this principle, we propose **ECO**, a framework that **E**volves **CO**re knowledge into modular, reusable neural components—termed *learngenes*—through similar evolutionary dynamics. To this end, we redefine learngenes as neural circuits and introduce Genetic Transfer Learning (GTL), a biologically inspired paradigm that establishes a genetic mechanism within neural networks in the context of supervised learning. GTL simulates evolutionary processes by generating diverse network populations, selecting high-performing individuals, and transferring their learngenes to subsequent generations. Through iterative refinement, GTL enables learngenes to accumulate transferable common knowledge. Extensive experiments show that ECO achieves efficient initialization and strong generalization across diverse models and tasks, while significantly reducing computational and memory costs compared to conventional methods.

Pseudo label based semi-supervised learning (SSL) for single-label and multi-label classification tasks has been extensively studied; however, semi-supervised label distribution learning (SSLDL) remains a largely unexplored area. Existing SSL methods fail in SSLDL because the pseudo-labels they generate only ensure overall similarity to the ground truth but do not preserve the ranking relationships between true labels, as they rely solely on KL divergence as the loss function during training. These skewed pseudo-labels lead the model to learn incorrect semantic relationships, resulting in reduced performance accuracy. To address these issues, we propose a novel SSLDL method called \textit{RankMatch}. \textit{RankMatch} fully considers the ranking relationships between different labels during the training phase with labeled data to generate higher-quality pseudo-labels. Furthermore, our key observation is that a flexible utilization of pseudo-labels can enhance SSLDL performance. Specifically, focusing solely on the ranking relationships between labels while disregarding their margins helps prevent model overfitting. Theoretically, we prove that incorporating ranking correlations enhances SSLDL performance and establish generalization error bounds for \textit{RankMatch}. Finally, extensive real-world experiments validate its effectiveness.

The rapid development of the Internet of Things (IoT) and wireless communication technologies has enabled the realization of vehicle-road cooperative systems. However, the vast amount of data generated by IoT devices in these systems poses challenges for traditional data processing methods. Augmented intelligence, such as deep reinforcement learning (DRL), has emerged as a powerful solution for processing large-scale real-time data and making accurate decisions. This article proposes an edge-cloud framework for vehicle-road cooperative traffic signal control in the context of Augmented IoT (AIoT). The framework integrates an edge-cloud collaborative resource allocation algorithm based on DRL and a traffic signal timing method that combines DRL with an extended Kalman filter. Simulation results demonstrate the effectiveness of the proposed framework in improving traffic efficiency and reducing vehicle waiting times. The average queue length was reduced by 35.7%, and the average waiting time increased by 29.1%. The proposed edge-cloud framework for vehicle-road cooperative traffic signal control in AIoT provides a promising solution for enhancing traffic management in smart cities.

Understanding how the brain responds to external stimuli and decoding this process has been a significant challenge in neuroscience. While previous studies typically concentrated on brain-to-image and brain-to-language reconstruction, our work strives to reconstruct gestures associated with speech stimuli perceived by brain. Unfortunately, the lack of paired {brain, speech, gesture} data hinders the deployment of deep learning models for this purpose. In this paper, we introduce a novel approach, fMRI2GES, that allows training of fMRI-to-gesture reconstruction networks on unpaired data using Dual Brain Decoding Alignment. This method relies on two key components: (i) observed texts that elicit brain responses, and (ii) textual descriptions associated with the gestures. Then, instead of training models in a completely supervised manner to find a mapping relationship among the three modalities, we harness an fMRIto- text model, a text-to-gesture model with paired data and an fMRI-to-gesture model with unpaired data, establishing dual fMRI-to-gesture reconstruction patterns. Afterward, we explicitly align two outputs and train our model in a self-supervision way. We show that our proposed method can reconstruct expressive gestures directly from fMRI recordings. We also investigate fMRI signals from different ROIs in the cortex and how they affect generation results. Overall, we provide new insights into decoding co-speech gestures, thereby advancing our understanding of neuroscience and cognitive science.

Label distribution learning (LDL) is a novel learning paradigm that assigns each instance with a label distribution. Although many specialized LDL algorithms have been proposed, few of them have noticed that the obtained label distributions are generally inaccurate with noise due to the difficulty of annotation. Besides, existing LDL algorithms overlooked that the noise in the inaccurate label distributions generally depends on instances. In this article, we identify the instance-dependent inaccurate LDL (IDI-LDL) problem and propose a novel algorithm called low-rank and sparse LDL (LRS-LDL). First, we assume that the inaccurate label distribution consists of the ground-truth label distribution and instance-dependent noise. Then, we learn a low-rank linear mapping from instances to the ground-truth label distributions and a sparse mapping from instances to the instance-dependent noise. In the theoretical analysis, we establish a generalization bound for LRS-LDL. Finally, in the experiments, we demonstrate that LRS-LDL can effectively address the IDI-LDL problem and outperform existing LDL methods.

Researchers have proposed to exploit label correlation to alleviate the exponential-size output space of label distribution learning (LDL). In particular, some have designed LDL methods to consider local label correlation. These methods roughly partition the training set into clusters and then exploit local label correlation on each one. Each sample belongs to one cluster and therefore has only one local label correlation. However, in real-world scenarios, the training samples may have fuzziness and belong to multiple clusters with blended local label correlations, which challenge these works. To solve this problem, we propose in LDL fuzzy label correlation (FLC)-each sample blends, with fuzzy membership, multiple local label correlations. First, we propose two types of FLCs, i.e., fuzzy membership-induced label correlation (FC) and joint fuzzy clustering and label correlation (FCC). Then, we put forward LDL-FC and LDL-FCC to exploit these two FLCs, respectively. Finally, we conduct extensive experiments to justify that LDL-FC and LDL-FCC statistically outperform state-of-the-art LDL methods.

Researchers have suggested leveraging label correlation to deal with the exponentially sized output space of label distribution learning (LDL). Among them, some have proposed to exploit local label correlation. They first partition the training set into different groups and then exploit local label correlation on each one. However, these works usually apply clustering algorithms, such as -means, to split the training set and obtain the clustering results independent of label correlation. The structures (e.g., low rank and manifold) learned on such clusters may not efficiently capture label correlation. To solve this problem, we put forward a novel LDL method called LDL by partitioning label distribution manifold (LDL-PLDM). First, it jointly bipartitions the training set and learns the label distribution manifold to model label correlation. Second, it recurses until the reconstruction error of learning the label distribution manifold cannot be reduced. LDL-PLDM achieves label-correlation-related partition results, on which the learned label distribution manifold can better capture label correlation. We conduct extensive experiments to justify that LDL-PLDM statistically outperforms state-of-the-art LDL methods.

In recent years, the merging of vast datasets with powerful computational resources has led to the emergence of large pre-trained models in the field of deep learning. However, the common practices often overgeneralize the applicability of these models, overlooking the task-specific resource constraints. To mitigate this issue, we propose \textbf{Cluster-Learngene}, which effectively clusters critical internal modules from a large ancestry model and then inherits them to initialize descendant models of elastic scales. Specifically, based on the density characteristics of attention heads, our method adaptively clusters attention heads of each layer and position-wise feed-forward networks (FFNs) in the ancestry model as the learngene. Moreover, we introduce priority weight-sharing and learnable parameter transformations that expand the learngene to initialize descendant models of elastic scales. Through extensive experimentation, we demonstrate that Cluster-Learngene not only is more efficient compared to other initialization methods but also customizes models of elastic scales according to downstream task resources.

Label distribution learning (LDL) trains a model to predict the relevance of a set of labels (called label distribution (LD)) to an instance. The previous LDL methods all assumed the LDs of the training instances are accurate. However, annotating highly accurate LDs for training instances is time-consuming and extremely expensive, and in reality the collected LDs are often inaccurate. This paper first investigates the inaccurate LDL (ILDL) problem—learn an LDL method from the inaccurate LDs. We assume that the inaccurate LD blends the ground-truth LD and sparse noise. Consequently, the ILDL problem becomes an inverse problem, whose objective is to recover the ground-truth LD and noise from the inaccurate LD. We hypothesize that the ground-truth LD exhibits low rank due to label correlations. Besides, we leverage the local geometric structure of instances (represented as graph) to further recover the ground-truth LD. Finally, the proposed method is formulated as a graph-regularized low-rank and sparse decomposition problem. Next, we induce an LDL predictive method by learning from recovered LD. Extensive experiments conducted on multiple datasets demonstrate the better performance of our method, especially for ILDL problem.

Label distribution learning (LDL) helps solve label ambiguity and has found wide applications. However, it may suffer from the challenge of objective inconsistency when adopted to classification problems because the learning objective of LDL is inconsistent with that of classification. Some LDL algorithms have been proposed to solve this issue, but they presume that label distribution can be represented by the maximum entropy model, which may not hold in many real-world problems. In this article, we design two novel LDL methods based on the k -nearest neighbors ( k NNs) approach without assuming any form of label distribution. First, we propose the large margin weighted k NN LDL (LW- k NNLDL). It learns a weight vector for the k NN algorithm to learn label distribution and implement a large margin to address the objective inconsistency. Second, we put forward the large margin distance-weighted k NN LDL (LD k NN-LDL) that learns distance-dependent weight vectors to consider the difference in the neighborhoods of different instances. Theoretical results show that our methods can learn any general-form label distribution. Moreover, extensive experimental studies validate that our methods significantly outperform state-of-the-art LDL approaches.

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.

The classic Paillier algorithm satisfies the security and additive homomorphism, allowing addition operations to be performed on the ciphertext. Paillier is widely used in various scenarios, especially in Federated Learning (FL), ensuring that the customer identity information is not exposed. However, its huge computational overhead reduces the training efficiency of FL. Hence, this paper proposes an improved Paillier algorithm that applies to FL. Specifically, the encryption generates noise based on the private key, and the ciphertexts are directly calculated based on pre-computation noise pools. During decryption, noise is eliminated through modular operations rather than modular exponentiation for faster decryption. Experimental results show that the encryption and decryption speeds are increased by 859x and 417x, respectively, when the key size is 2048. Then, we combined the improved Paillier algorithm with the BatchCrypt scheme, demonstrating that our algorithm accelerates BatchCrypt by approximately 10-14x.

Robust few-shot learning (RFSL), which aims to address noisy labels in few-shot learning, has recently gained considerable attention. Existing RFSL methods are based on the assumption that the noise comes from known classes (in-domain), which is inconsistent with many real-world scenarios where the noise does not belong to any known classes (out-of-domain). We refer to this more complex scenario as open-world few-shot learning (OFSL), where in-domain and out-of-domain noise simultaneously exists in few-shot datasets. To address the challenging problem, we propose a unified framework to implement comprehensive calibration from instance to metric. Specifically, we design a dual-networks structure composed of a contrastive network and a meta network to respectively extract feature-related intra-class information and enlarged inter-class variations. For instance-wise calibration, we present a novel prototype modification strategy to aggregate prototypes with intra-class and inter-class instance reweighting. For metric-wise calibration, we present a novel metric to implicitly scale the per-class prediction by fusing two spatial metrics respectively constructed by the two networks. In this way, the impact of noise in OFSL can be effectively mitigated from both feature space and label space. Extensive experiments on various OFSL settings demonstrate the robustness and superiority of our method. Our source codes is available at https://github.com/anyuexuan/IDEAL.

Label correlation is helpful to alleviate the overwhelming output space of label distribution learning (LDL). However, existing studies either only consider one of global and local label correlations or exploit label correlation by some prior knowledge (e.g., low-rank assumption, which may not hold sometimes). To efficiently exploit both global and local label correlations in a data-driven way, we propose in this article a new LDL method called label distribution learning by exploiting label distribution manifold (LDL-LDM). Our basic idea is that the underlying manifold structure of label distribution may encode the correlations among labels. LDL-LDM works as follows. First, to exploit global label correlation, we learn the label distribution manifold and encourage the outputs of our model to lie in the same manifold. Second, we learn the label distribution manifold of different clusters of samples to consider local label correlations. Third, to handle incomplete label distribution learning (incomplete LDL), we jointly learn label distribution and label distribution manifold. Theoretical analysis demonstrates the generalization of our method. Finally, experimental results validate the effectiveness of LDL-LDM in both full and incomplete LDL cases.

Label ambiguity has attracted quite some attention among the machine learning community. The latterly proposed Label Distribution Learning (LDL) can handle label ambiguity and has found wide applications in real classification problems. In the training phase, an LDL model is learned first. In the test phase, the top label(s) in the label distribution predicted by the learned LDL model is (are) then regarded as the predicted label(s). That is, LDL considers the whole label distribution in the training phase, but only the top label(s) in the test phase, which likely leads to objective inconsistency. To avoid such inconsistency, we propose a new LDL method Re-Weighting Large Margin Label Distribution Learning (RWLM-LDL). First, we prove that the expected$ L_1 $-norm loss of LDL bounds the classification error probability, and thus apply$ L_1 $-norm loss as the learning metric. Second, re-weighting schemes are put forward to alleviate the inconsistency. Third, large margin is introduced to further solve the inconsistency. The theoretical results are presented to showcase the generalization and discrimination of RWLM-LDL. Finally, experimental results show the statistically superior performance of RWLM-LDL against other comparing methods.

Although Label Distribution Learning (LDL) has witnessed extensive classification applications, it faces the challenge of objective mismatch – the objective of LDL mismatches that of classification, which has seldom been noticed in existing studies. Our goal is to solve the objective mismatch and improve the classification performance of LDL. Specifically, we extend the margin theory to LDL and propose a new LDL method called \textbf{L}abel \textbf{D}istribution \textbf{L}earning \textbf{M}achine (LDLM). First, we define the label distribution margin and propose the \textbf{S}upport \textbf{V}ector \textbf{R}egression \textbf{M}achine (SVRM) to learn the optimal label. Second, we propose the adaptive margin loss to learn label description degrees. In theoretical analysis, we develop a generalization theory for the SVRM and analyze the generalization of LDLM. Experimental results validate the better classification performance of LDLM.

Although Label Distribution Learning (LDL) has found wide applications in varieties of classification problems, it may face the challenge of objective mismatch -- LDL neglects the optimal label for the sake of learning the whole label distribution, which leads to performance deterioration. To improve classification performance and solve the objective mismatch, we propose a new LDL algorithm called LDL-HR. LDL-HR provides a new perspective of label distribution, \textit{i.e.}, a combination of the \textbf{highest label} and the \textbf{rest label description degrees}. It works as follows. First, we learn the highest label by fitting the degenerated label distribution and large margin. Second, we learn the rest label description degrees to exploit generalization. Theoretical analysis shows the generalization of LDL-HR. Besides, the experimental results on 18 real-world datasets validate the statistical superiority of our method.

As a novel learning paradigm, label distribution learning (LDL) explicitly models label ambiguity with the definition of label description degree. Although lots of work has been done to deal with real-world applications, theoretical results on LDL remain unexplored. In this paper, we rethink LDL from theoretical aspects, towards analyzing learnability of LDL. Firstly, risk bounds for three representative LDL algorithms (AA-kNN, AA-BP and SA-ME) are provided. For AA-kNN, Lipschitzness of the label distribution function is assumed to bound the risk, and for AA-BP and SA-ME, rademacher complexity is utilized to give data-dependent risk bounds. Secondly, a generalized plug-in decision theorem is proposed to understand the relation between LDL and classification, uncovering that approximation to the conditional probability distribution function in absolute loss guarantees approaching to the optimal classifier, and also data-dependent error probability bounds are presented for the corresponding LDL algorithms to perform classification. As far as we know, this is perhaps the first research on theory of LDL.

Label Distribution Learning (LDL) is a novel learning paradigm, aim of which is to minimize the distance between the model output and the ground-truth label distribution. We notice that, in real-word applications, the learned label distribution model is generally treated as a classification model, with the label corresponding to the highest model output as the predicted label, which unfortunately prompts an inconsistency between the training phrase and the test phrase. To solve the inconsistency, we propose in this paper a new Label Distribution Learning algorithm for Classification (LDL4C). Firstly, instead of KL-divergence, absolute loss is applied as the measure for LDL4C. Secondly, samples are re-weighted with information entropy. Thirdly, large margin classifier is adapted to boost discrimination precision. We then reveal that theoretically LDL4C seeks a balance between generalization and discrimination. Finally, we compare LDL4C with existing LDL algorithms on 17 real-word datasets, and experimental results demonstrate the effectiveness of LDL4C in classification.

Partial label (PL) learning aims to induce a multi-class classifier from training examples where each of them is associated with a set of candidate labels, among which only one is valid. It is well-known that the problem of class-imbalance stands as a major factor affecting the generalization performance of multi-class classifier, and this problem becomes more pronounced as the ground-truth label of each PL training example is not directly accessible to the learning approach. To mitigate the negative influence of class-imbalance to partial label learning, a novel class-imbalance aware approach named CIMAP is proposed by adapting over-sampling techniques for handling PL training examples. Firstly, for each PL training example, CIMAP disambiguates its candidate label set by estimating the confidence of each class label being ground-truth one via weighted k-nearest neighbor aggregation. After that, the original PL training set is replenished for model induction by over-sampling existing PL training examples via manipulation of the disambiguation results. Extensive experiments on artificial as well as real-world PL data sets show that CIMAP serves as an effective data-level approach to mitigate the class-imbalance problem for partial label learning.