Spiking Federated Learning (SFL) has been widely studied with the energy efficiency of Spiking Neural Networks (SNNs). However, existing SFL methods require model homogeneity and assume all clients have sufficient computational resources, resulting in the exclusion of some resource-constrained clients. To address the prevalent system heterogeneity in real-world scenarios, enabling heterogeneous SFL systems that allow clients to adaptively deploy models of different scales based on their local resources is crucial. To this end, we introduce SFedHIFI, a novel Spiking Federated Learning framework with Fire Rate-Based Heterogeneous Information Fusion. Specifically, SFedHIFI employs channel-wise matrix decomposition to deploy SNN models of adaptive complexity on clients with heterogeneous resources. Building on this, the proposed heterogeneous information fusion module enables cross-scale aggregation among models of different widths, thereby enhancing the utilization of diverse local knowledge. Extensive experiments on three public benchmarks demonstrate that SFedHIFI can effectively enable heterogeneous SFL, consistently outperforming all three baseline methods. Compared with ANN-based FL, it achieves significant energy savings with only a marginal trade-off in accuracy.

Session-based recommendation (SBR) aims to predict anonymous users' next interaction based on their interaction sessions. In practical recommendation scenario, low-exposure items constitute the majority of interactions, creating a long-tail distribution that severely compromises recommendation diversity. Existing approaches attempt to address this issue by promoting tail items but incur accuracy degradation, exhibiting a "see-saw" effect between long-tail and accuracy performance. We attribute such conflict to session-irrelevant noise within the tail item set, which existing long-tail approaches fail to identify and constrain effectively. To resolve our fundamental conflict, we propose HID (Hybrid Intent-based Dual Constraint Framework), a plug-and-play framework that transforms the conventional "see-saw" into a "win-win" relationship through introducing the hybrid intent-based dual constraints. Two key innovations are incorporated in this framework: (i) Hybrid Intent Learning, where we reformulate the intent extraction strategies by employing attribute-aware spectral clustering to reconstruct the item-to-intent mapping. Furthermore, discrimination of session-irrelevant noise is achieved through the assignment of both target and noise intents to each sessions. (ii) Intent Constraint Loss, where we propose two novel constraint paradigms regarding the diversity and accuracy to regulate the representation learning process, and unify the two optimization objectives into a unique loss. Extensive experiments across multiple SBR models and datasets demonstrate that HID can enhance both long-tail performance and recommendation accuracy, establishing new state-of-the-art performance in long-tail recommender systems.

Multimodal Emotion Recognition (MER) aims to accurately identify human emotional states by integrating heterogeneous modalities such as visual, auditory, and textual data. Existing approaches predominantly rely on unified emotion labels to supervise model training, often overlooking a critical challenge: inter-modal emotion conflicts, wherein different modalities within the same sample may express divergent emotional tendencies. In this work, we address this overlooked issue by proposing a novel framework, Typicality-based Consistent-aware Multimodal Emotion Recognition (TiCAL), inspired by the stage-wise nature of human emotion perception. TiCAL dynamically assesses the consistency of each training sample by leveraging pseudo unimodal emotion labels alongside a typicality estimation. To further enhance emotion representation, we embed features in a hyperbolic space, enabling the capture of fine-grained distinctions among emotional categories. By incorporating consistency estimates into the learning process, our method improves model performance, particularly on samples exhibiting high modality inconsistency. Extensive experiments on benchmark datasets, e.g, MOSEI and MER2023, validate the effectiveness of TiCAL in mitigating inter-modal emotional conflicts and enhancing overall recognition accuracy, e.g., with about 2.6% improvements over the state-of-the-art DMD.

The "Fine-Tuning-as-a-Service" paradigm exposes large language models to catastrophic safety degradation from less harmful samples.Alignment-stage defenses address this by proactively injecting adversarial perturbations to bolster the model's inherent robustness against harmful drift.However, existing methods rely on perturbation directions that often conflict with harmful gradients, inadvertently facilitating the acquisition of malicious features rather than suppressing them.To address this issue, we propose Orthogonal and Adaptive Safety Alignment Strategy (OASIS) to mathematically decouple safety enforcement from harmful feature acquisition.By projecting perturbations orthogonal to harmful gradients and concentrating optimization on adaptively selected safetycritical layers, OASIS effectively resolves directional conflicts while maximizing parameter efficiency.Extensive experiments on four LLMs across three datasets (SST2, GSM8K, and AGNews) demonstrate that OASIS reduces the Harmful Score by approximately 60% compared to competitive baselines, while maintaining stable downstream task utility.Our code is publicly available at https://github. com/xiaoroyi/OASIS.

The spiking federated learning (FL) is an emerging distributed learning paradigm that allows resource-constrained devices to train collaboratively at low power consumption without exchanging local data. It takes advantage of both the privacy computation property in FL and the energy efficiency in spiking neural networks (SNNs). However, existing spiking FL methods employ a random selection approach for client aggregation, assuming unbiased client participation. This neglect of statistical heterogeneity significantly affects the convergence and precision of the global model. In this work, we propose a credit assignment-based active client selection strategy for spiking federated learning, the SFedCA, to aggregate clients contributing to the global sample distribution balance judiciously. Specifically, the client credits are assigned by the firing intensity state before and after local model training, which reflects the difference in local data distribution from the global model. The comprehensive experiments are conducted on various non-identical and independent distribution (non-IID) scenarios. The experimental results demonstrate that the SFedCA outperforms the existing state-of-the-art spiking FL methods and requires fewer communication rounds.

Session-based recommendation (SBR) predicts the next interaction of anonymous users based on their session data. In practical scenarios, low-exposure tail items constitute the majority of interactions, leading to the biased recommendation whereby a small set of high-exposure head items is preferentially recommended. Existing solutions focus on promoting those tail items but with a sacrifice in recommendation accuracy. We attribute such a tradeoff to session-irrelevant noise within the tail items, which existing long-tail approaches fail to identify and constrain effectively. To resolve this fundamental conflict, we propose Hybrid Intent-based Dual Constraint framework (HID) , a plug-and-play framework that converts the traditional tradeoff between long-tail performance and accuracy into a synergistic relationship by introducing hybrid intent-based dual constraints. HID incorporates two key innovations: (i) Hybrid Intent Learning , which reformulates intent extraction through attribute-aware spectral clustering and discriminates session-irrelevant noise by assigning target and noise intents to each session and (ii) Intent Constraint Loss , which introduces two constraints—diversity and accuracy—to regulate item and session representation learning. These two objectives are unified into a single training loss through rigorous theoretical derivation. To handle ambiguous user intent in the real-world, we also propose a slack version of HID. Extensive experiments show that HID enhances both long-tail performance and accuracy, establishing new state-of-the-art performance in long-tail recommender systems. The implementation code is available at: https://github.com/jarviswww/Code4TradeSynergy .

Contemporary deep learning, characterized by the training of cumbersome neural networks on massive datasets, confronts substantial computational hurdles. To alleviate heavy data storage burdens on limited hardware resources, numerous dataset compression methods such as dataset distillation (DD) and coreset selection have emerged to obtain a compact but informative dataset through synthesis or selection for efficient training. However, DD involves an expensive optimization procedure and exhibits limited generalization across unseen architectures, while coreset selection is limited by its low data keep ratio and reliance on heuristics, hindering its practicality and feasibility. To address these limitations, we introduce a newly versatile framework for dataset compression, namely Adaptive Dataset Quantization (ADQ). Specifically, we first identify the sub-optimal performance of naive Dataset Quantization (DQ), which relies on uniform sampling and overlooks the varying importance of each generated bin. Subsequently, we propose a novel adaptive sampling strategy through the evaluation of generated bins' representativeness score, diversity score and importance score, where the former two scores are quantified by the texture level and contrastive learning-based techniques, respectively. Extensive experiments demonstrate that our method not only exhibits superior generalization capability across different architectures, but also attains state-of-the-art results.

Personalized federated learning (PFL) is a new paradigm to address the statistical heterogeneity problem in federated learning. Most existing PFL methods focus on leveraging global and local information such as model interpolation or parameter decoupling. However, these methods often overlook the generalization potential during local client learning. From a local optimization perspective, we propose a simple and general PFL method, Federated learning with Flexible Sharpness-Aware Minimization (FedFSA). Specifically, we emphasize the importance of applying a larger perturbation to critical layers of the local model when using the Sharpness-Aware Minimization (SAM) optimizer. Then, we design a metric, perturbation sensitivity, to estimate the layer-wise sharpness of each local model. Based on this metric, FedFSA can flexibly select the layers with the highest sharpness to employ larger perturbation. Extensive experiments are conducted on four datasets with two types of statistical heterogeneity for image classification. The results show that FedFSA outperforms seven state-of-the-art baselines by up to 8.26% in test accuracy. Besides, FedFSA can be applied to different model architectures and easily integrated into other federated learning methods, achieving a 4.45% improvement.

The growing demand for efficient deep learning has positioned dataset distillation as a pivotal technique for compressing training dataset while preserving model performance. However, existing inner-loop optimization methods for dataset distillation typically rely on random truncation strategies, which lack flexibility and often yield suboptimal results. In this work, we observe that neural networks exhibit distinct learning dynamics across different training stages—early, middle, and late—making random truncation ineffective. To address this limitation, we propose Automatic Truncated Backpropagation Through Time (AT-BPTT), a novel framework that dynamically adapts both truncation positions and window sizes according to intrinsic gradient behavior. AT-BPTT introduces three key components: (1) a probabilistic mechanism for stage-aware timestep selection, (2) an adaptive window sizing strategy based on gradient variation, and (3) a low-rank Hessian approximation to reduce computational overhead. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-1K show that AT-BPTT achieves state-of-the-art performance, improving accuracy by an average of 6.16\% over baseline methods. Moreover, our approach accelerates inner-loop optimization by 3.9 × while saving 63\% memory cost.

Large language models (LLMs) have gained a lot of attention and achievements recently because of their significant comprehension and generative abilities. However, the large-scale parameters of LLMs require considerable computational resources in the training and inference process, which restricts their wide application. To overcome this challenge, we propose an efficient mixed precision weight quantization (EMWQ) method for LLMs in this article. Specifically, we introduce a new outlier detection method by analyzing the weight distribution instead of the conventional weight magnitude. Then, we propose a dual-quantization strategy that quantizes both the outlier critical columns and the residual matrices with different precision. Besides, we introduce two effective EMWQ-based application frameworks, the EMWQ-R and EMWQ-O in our study. Comprehensive experiments are conducted on the Penn Treebank (PTB), C4, ARC-Easy datasets, and MMLU benchmark across various tasks. The comparison results demonstrate that the proposed EMWQ achieves state-of-the-art performance in mixed precision quantization and further reduces computational memory cost. Besides, it has higher generalizability compared with conventional methods.

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ synthesized training data are prone to the limitations of inadequate diversity and discrepancies in distribution between the synthesized and original datasets. To address these challenges, this paper introduces an innovative approach to DFKD through diverse diffusion augmentation (DDA). Specifically, we revise the paradigm of common data synthesis in DFKD to a composite process through leveraging diffusion models subsequent to data synthesis for self-supervised augmentation, which generates a spectrum of data samples with similar distributions while retaining controlled variations. Furthermore, to mitigate excessive deviation in the embedding space, we introduce an image filtering technique grounded in cosine similarity to maintain fidelity during the knowledge distillation process. Comprehensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets showcase the superior performance of our method across various teacher-student network configurations, outperforming the contemporary state-of-the-art DFKD methods. Code will be available at: https://github.com/SLGSP/DDA.

Recent advances in bio-inspired vision with event cameras and associated spiking neural networks (SNNs) have provided promising solutions for low-power consumption neuromorphic tasks. However, as the research of event cameras is still in its infancy, the amount of labeled event stream data is much less than that of the RGB database. The traditional method of converting static images into event streams by simulation to increase the sample size cannot simulate the characteristics of event cameras such as high temporal resolution. To take advantage of both the rich knowledge in labeled RGB images and the features of the event camera, we propose a transfer learning method from the RGB to the event domain in this paper. Specifically, we first introduce a transfer learning framework named R2ETL (RGB to Event Transfer Learning), including a novel encoding alignment module and a feature alignment module. Then, we introduce the temporal centered kernel alignment (TCKA) loss function to improve the efficiency of transfer learning. It aligns the distribution of temporal neuron states by adding a temporal learning constraint. Finally, we theoretically analyze the amount of data required by the deep neuromorphic model to prove the necessity of our method. Numerous experiments demonstrate that our proposed framework outperforms the state-of-the-art SNN and artificial neural network (ANN) models trained on event streams, including N-MNIST, CIFAR10-DVS and N-Caltech101. This indicates that the R2ETL framework is able to leverage the knowledge of labeled RGB images to help the training of SNN on event streams.

Traditional spiking learning algorithm aims to train neurons to spike at a specific time or on a particular frequency, which requires precise time and frequency labels in the training process. While in reality, usually only aggregated labels of sequential patterns are provided. The aggregate-label (AL) learning is proposed to discover these predictive features in distracting background streams only by aggregated spikes. It has achieved much success recently, but it is still computationally intensive and has limited use in deep networks. To address these issues, we propose an event-driven spiking aggregate learning algorithm (SALA) in this article. Specifically, to reduce the computational complexity, we improve the conventional spike-threshold-surface (STS) calculation in AL learning by analytical calculating voltage peak values in spiking neurons. Then we derive the algorithm to multilayers by event-driven strategy using aggregated spikes. We conduct comprehensive experiments on various tasks including temporal clue recognition, segmented and continuous speech recognition, and neuromorphic image classification. The experimental results demonstrate that the new STS method improves the efficiency of AL learning significantly, and the proposed algorithm outperforms the conventional spiking algorithm in various temporal clue recognition tasks.

A large quantity of labeled data is required to train high-performance deep spiking neural networks (SNNs), but obtaining labeled data is expensive. Active learning is proposed to reduce the quantity of labeled data required by deep learning models. However, conventional active learning methods in SNNs are not as effective as that in conventional artificial neural networks (ANNs) because of the difference in feature representation and information transmission. To address this issue, we propose an effective active learning method for a deep SNN model in this article. Specifically, a loss prediction module ActiveLossNet is proposed to extract features and select valuable samples for deep SNNs. Then, we derive the corresponding active learning algorithm for deep SNN models. Comprehensive experiments are conducted on CIFAR-10, MNIST, Fashion-MNIST, and SVHN on different SNN frameworks, including seven-layer CIFARNet and 20-layer ResNet-18. The comparison results demonstrate that the proposed active learning algorithm outperforms random selection and conventional ANN active learning methods. In addition, our method converges faster than conventional active learning methods.

As the third-generation neural networks, spiking neural networks (SNNs) have great potential on neuromorphic hardware because of their high energy efficiency. However, deep spiking reinforcement learning (DSRL), that is, the reinforcement learning (RL) based on SNNs, is still in its preliminary stage due to the binary output and the nondifferentiable property of the spiking function. To address these issues, we propose a deep spiking Q -network (DSQN) in this article. Specifically, we propose a directly trained DSRL architecture based on the leaky integrate-and-fire (LIF) neurons and deep Q -network (DQN). Then, we adapt a direct spiking learning algorithm for the DSQN. We further demonstrate the advantages of using LIF neurons in DSQN theoretically. Comprehensive experiments have been conducted on 17 top-performing Atari games to compare our method with the state-of-the-art conversion method. The experimental results demonstrate the superiority of our method in terms of performance, stability, generalization and energy efficiency. To the best of our knowledge, our work is the first one to achieve state-of-the-art performance on multiple Atari games with the directly trained SNN.

As the third generation of neural networks, spiking neural networks (SNNs) have gained much attention recently because of their high energy efficiency on neuromorphic hardware. However, training deep SNNs requires many labeled data that are expensive to obtain in real-world applications, as traditional artificial neural networks (ANNs). In order to address this issue, transfer learning has been proposed and widely used in traditional ANNs, but it has limited use in SNNs. In this article, we propose an effective transfer learning framework for deep SNNs based on the domain in-variance representation. Specifically, we analyze the rationality of centered kernel alignment (CKA) as a domain distance measurement relative to maximum mean discrepancy (MMD) in deep SNNs. In addition, we study the feature transferability across different layers by testing on the Office-31, Office-Caltech-10, and PACS datasets. The experimental results demonstrate the transferability of SNNs and show the effectiveness of the proposed transfer learning framework by using CKA in SNNs.

The spiking neural network (SNN) is the third generation of neural networks and performs remarkably well in cognitive tasks, such as pattern recognition. The temporal neural encode mechanism found in biological hippocampus enables SNN to possess more powerful computation capability than networks with other encoding schemes. However, this temporal encoding approach requires neurons to process information serially on time, which reduces learning efficiency significantly. To keep the powerful computation capability of the temporal encoding mechanism and to overcome its low efficiency in the training of SNNs, a new training algorithm, the accurate synaptic-efficiency adjustment method is proposed in this paper. Inspired by the selective attention mechanism of the primate visual system, our algorithm selects only the target spike time as attention areas, and ignores voltage states of the untarget ones, resulting in a significant reduction of training time. Besides, our algorithm employs a cost function based on the voltage difference between the potential of the output neuron and the firing threshold of the SNN, instead of the traditional precise firing time distance. A normalized spike-timing-dependent-plasticity learning window is applied to assigning this error to different synapses for instructing their training. Comprehensive simulations are conducted to investigate the learning properties of our algorithm, with input neurons emitting both single spike and multiple spikes. Simulation results indicate that our algorithm possesses higher learning performance than the existing other methods and achieves the state-of-the-art efficiency in the training of SNN.

Since the great mathematician Leonhard Euler initiated the study of graph theory, the network has been one of the most significant research subject in multidisciplinary. In recent years, the proposition of the small-world and scale-free properties of complex networks in statistical physics made the network science intriguing again for many researchers. One of the challenges of the network science is to propose rational models for complex networks. In this paper, in order to reveal the influence of the vertex generating mechanism of complex networks, we propose three novel models based on the homogeneous Poisson, nonhomogeneous Poisson and birth death process, respectively, which can be regarded as typical scale-free networks and utilized to simulate practical networks. The degree distribution and exponent are analyzed and explained in mathematics by different approaches. In the simulation, we display the modeling process, the degree distribution of empirical data by statistical methods, and reliability of proposed networks, results show our models follow the features of typical complex networks. Finally, some future challenges for complex systems are discussed.