Few-shot class-incremental learning (FSCIL) presents a greater challenge compared with few-shot task-incremental learning (FSTIL) due to the need to classify all previous classes without prior knowledge of the session identifier (session-ID). To address this, we propose Bamboo, a novel framework for FSCIL that introduces a cascading inference mechanism to explicitly infer the session-ID for each sample. This mechanism is enabled by a novel, session-specific equiangular tight frame prototype (ETF-P) classifier. By adaptively fusing session-agnostic and session-specific semantics, the ETF-P classifier reliably determines if a sample belongs to its associated session, which is the core decision required at each step of the cascade. Considering the incremental nature of the learning process, which resembles the continuous growth of bamboo, we treat the base session classifier as the foundational bamboo node and progressively add new session classifiers as additional nodes on top. During the testing phase, each sample flows sequentially through the bamboo nodes, from top to bottom, to determine its session-ID and to be classified accordingly. Overall, the Bamboo framework is capable of perceiving session-ID without prior knowledge and classifying each sample within the correct session, leading to state-of-the-art performance on multiple benchmark datasets.

The integrated sensing and communication (ISAC) technology has gained increasing attention in recent years due to its excellent performance of increasing the spectrum and hardware efficiencies. In this paper, we investigate the joint optimization of beam selection and digital beamforming for a millimeter-wave (mmWave) ISAC system to simultaneously improve the performance of communication and sensing. We propose a novel hybrid beamforming scheme based on deep learning by maximizing the sum of communication mutual information (CMI) and sensing mutual information (SMI) to enable multi-user multiple-input multiple-output (MU-MIMO) communication and multiple-input single-output (MISO) radar sensing. Specially, we propose a joint deep reinforcement learning and unfolding network (DRL-UN) to optimize the beam selection and digital beamforming matrices at the base station (BS) in an ISAC system. Simulation results demonstrate that the proposed hybrid beamforming scheme significantly outperforms the existing algorithms in terms of sensing and communication (S&C) sum-rate in a mmWave ISAC system.

Few-shot class-incremental learning (FSCIL) requires learning new knowledge without forgetting old knowledge. Forward compatibility can reserve space for novel classes while maintaining base class knowledge in incremental learning. Better forward compatibility is crucial for effectively mastering all knowledge, especially when dealing with a few unknown new classes. In this article, we propose the better forward compatibility pretraining (BFCP) to further enhance forward compatibility in FSCIL. We adopt a two-stage training for the backbone network in the base session. First, we train the backbone network at the image-level to enhance its feature extraction capability, enabling the model to extract valuable information from unknown class images. Second, we fine-tune the backbone network at the feature-level with fake prototypes and instances to achieve clustering base classes and reserve space for unknown new classes. For all incremental new sessions, we freeze the backbone network and employ prototype rectification without further training to refine the prototypes of the novel classes. We conduct extensive experiments with different input scales, including federated cross-domain pretraining and cross-domain class-incremental experiments. BFCP efficiently handles both novel and base classes of each incremental session and significantly outperforms state-of-the-art methods, achieving an average accuracy of 63.47% on the CIFAR100 dataset.

Task-incremental learning methods that adopt knowledge distillation face two significant challenges: confidence bias and knowledge loss. These challenges make it difficult to effectively balance the stability and plasticity of the network in the incremental learning process. In this article, we propose double confidence calibration focused distillation (DCCFD) to address these challenges. We introduce intratask and intertask confidence calibration (ECC) modules that can mitigate network overconfidence during incremental learning and reduce the degree of feature representation bias. We also propose a focused distillation (FD) module that can alleviate the problem of knowledge loss during the task increment process, improving model stability without reducing plasticity. Experimental results on the CIFAR-100, TinyImageNet, and CORE-50 datasets demonstrate the effectiveness of our method, with performance that matches or exceeds the state of the art. Furthermore, our method can be used as a plug-and-play module to consistently improve class-incremental learning methods.

Few-shot learning (FSL) is challenging due to the scarce labeled novel-class data. Researchers have to train the embedding function with auxiliary base-class data to obtain the novel-class embeddings. However, the domain gap makes the novel-class embedding unsatisfactory, as the novel class and the base class are disjoint. Recent studies prove that embedding rectification shows great potential, introduces miscellaneous variants, and achieves similar performances. Nonetheless, while each method demonstrates unique strengths, they often address distinct challenges in isolation, limiting their applicability in more complex or diverse scenarios. In this article, we take a closer look at these methods and hypothesize that a general embedding rectification framework is more essential to the model's performance. To verify our observation, we propose: 1) a distribution propagation (DisP) layer distinguishes the inter-class margin and increases intra-class aggregation, performing the task-level rectification; and 2) a prototype propagation (ProtoP) layer moves the prototype toward the ideal class center, applying the prototype-query level rectification. Our framework aims to maximize the actual data distribution. Although pseudo-labeling proves effective in achieving this goal, a significant challenge is ensuring the reliable retention of only high-confidence predictions. To overcome this, we introduce a distribution-based pseudo-labeling method pseudo-query upgrade (PseQUp) that provides more reliable pseudo-labeling samples without relying on confidence scores. We evaluate the proposed method in both transfer learning and meta-learning scenarios. Empirical experiments show the applicable and plug-and-play ability of the proposed methods.

Geometry studies the spatial structure and location information of objects, providing a priori knowledge and intuitive explanation for classification methods. Considering samples from a geometric perspective offers a novel approach to understanding their information. In this article, we propose a method called local-global geometric information and view complementarity introduced multiview metric learning (GIVCMML). Our method effectively exploits the geometric information of multiview samples. The learned metric space retains the geometric relations of samples and makes them more separable. First, we propose the global geometrical constraint in the maximum margin criterion framework. By maximizing the distance between class centers in the metric space, we ensure that samples from different classes are well separated. Second, to maintain the manifold structure of the original space, we build an adjacency matrix that contains the sample label information. This helps explore the local geometric information of sample pairs. Finally, to better mine the complementary information of multiview samples, GIVCMML maximizes the correlation between each view in the metric space. This enables each view to adaptively learn from the others and explore the complementary information between views. We extensively evaluate the effectiveness of our method on real-world datasets. The experimental results demonstrate that GIVCMML achieves competitive performance compared with multiview metric learning (MvML) methods.

Federated Continual Learning (FCL) approaches exist two major problems of the probability bias and the imbalance in parameter variations. These two problems lead to catastrophic forgetting of the network in the FCL process . Therefore, this paper proposes a novel FCL framework, Federated Probability Memory Recall (FedPMR), to mitigate the probability bias problem and the imbalance in parameter variations. Firstly, for the probability bias problem, this paper designs the Probability Distribution Alignment (PDA) module, which consolidates the memory of old probability experience. Specifically, PDA maintains a replay buffer and uses the probability memory stored in the buffer to correct the offset probabilities of the previous tasks during the two-stage training. Secondly, to alleviate the imbalance in parameter variations, this paper designs the Parameter Consistency Constraint (PCC) module, which constrains the magnitude of neural weight changes for previous tasks. Concretely, PCC applies a set of adaptive weights to subsets of the regularization term that constrains parameter changes, forcing the current model to be sufficiently close to the past model in parameter space distance. Experiments with various levels of task similitude across clients demonstrate that our technique establishes the new state-of-the-art performance when compared to previous FCL approaches.

Recently, electroencephalogram (EEG) emotion recognition has gradually attracted a lot of attention. This brief designs a novel frame-level teacher-student framework with data privacy (FLTSDP) for EEG emotion recognition. The framework first proposes a teacher-student network without prior professional information for automated filtering of useful frame-level features by a gated mechanism and extracting high-level features by using knowledge distillation to capture the results of EEG emotion recognition from a teacher network and student networks. Then, the results from subnetworks are integrated by using the novel decision module, which, motivated by the voting mechanism, adjusts the composition of feature vectors and improves the weight of accurate prediction to optimize the integration effect. During training, an innovative data privacy protection mechanism is applied for avoiding data sharing, where each student network only inherits weights from all trained networks and does not inherit the training dataset. Here, the framework can be repeatedly optimized and improved by only training the next student subnetwork on new EEG signals. Experimental results show that our framework improves the accuracy of EEG emotion recognition by more than 5% and gets state-of-the-art performance for EEG emotion recognition in the subject-independent mode.

One of the most effective approaches to improving the performance of a machine learning model is to procure additional training data. A model owner seeking relevant training data from a data owner needs to appraise the data before acquiring it. However, without a formal agreement, the data owner does not want to share data. The resulting Catch-22 prevents efficient data markets from forming. This paper proposes adding a data appraisal stage that requires no data sharing between data owners and model owners. Specifically, we use multi-party computation to implement an appraisal function computed on private data. The appraised value serves as a guide to facilitate data selection and transaction. We propose an efficient data appraisal method based on forward influence functions that approximates data value through its first-order loss reduction on the current model. The method requires no additional hyper-parameters or re-training. We show that in private, forward influence functions provide an appealing trade-off between high quality appraisal and required computation, in spite of label noise, class imbalance, and missing data. Our work seeks to inspire an open market that incentivizes efficient, equitable exchange of domain-specific training data.

In few-shot learning, methods are enslaved to the scarce labeled data, resulting in suboptimal embedding. Recent studies learn the embedding network by other large-scale labeled data. However, the trained network may give rise to the distorted embedding of target data. We argue two respects are required for an unprecedented and promising solution. We call them Better Embedding and More Shots (BEMS). Suppose we propose to extract embedding from the embedding network. BE maximizes the extraction of general representation and prevents over-fitting information. For this purpose, we introduce the topological relation for global reconstruction, avoiding excessive memorizing. MS maximizes the relevance between the reconstructed embedding and the target class space. In this respect, increasing the number of shots is a pivotal but intractable strategy. As a creative method, we derive the bound of information-theory-based loss function and implicitly achieve infinite shots with negligible cost. A substantial experimental analysis is carried out to demonstrate the state-of-the-art performance. Compared to the baseline, our method improves by up to 10%+. We also prove that BEMS is suitable for both standard pre-trained and meta-learning embedded networks.

Support Vector Data Description (SVDD) is an extremely hot topic issue in One-Class Classification (OCC), which has displayed outstanding performance in dealing with many novelty detection problems. However, SVDD just takes the data description by the kernel-based distance among each instance into consideration rather than considering the distribution of the data. Therefore, Fuzzy Support Vector Data Description (Fuzzy-SVDD) has been developed to distribute a fuzzy membership to each input sample so that different samples cause different contributions to classification boundary. The majority of the methods in Fuzzy-SVDD are based on the sample density, but there are remaining two problems. These density-based Fuzzy-SVDD methods would decrease the contribution of support vectors (SVs) in low densities. What is more, these methods cannot get a precise density when there are few target samples. These two problems would lead to a poor classification boundary. To overcome these drawbacks, a novel method called Boundary-based Fuzzy-SVDD (BF-SVDD) is proposed in this paper. BF-SVDD uses a new definition called local–global center distance to search for the samples near the boundary. Then, it enhances fuzzy memberships of these samples because they carry more significant information for the decision boundary than other data. The contribution of this paper can be summarized into three main points. First a novel concept called local–global center distances is proposed to find the SVs better. Second, fuzzy memberships with local–global center distance make SVs more informative to create the decision boundary. Furthermore, the experiments based on University of California, Irvine and Knowledge Extraction based on Evolutionary Learning also show that the proposed method has excellent performances. Even for the minority class in imbalance data sets, the proposed method can also have a good classification.