Pathology images are considered the ``gold standard" for cancer diagnosis and treatment, with gigapixel images providing extensive tissue and cellular information. Existing methods fail to simultaneously extract global structural and local detail features for comprehensive pathology image analysis efficiently. To address these limitations, we propose a self-calibration enhanced framework for whole slide pathology image analysis, comprising three components: a global branch, a focus predictor, and a detailed branch. The global branch initially classifies using the pathological thumbnail, while the focus predictor identifies relevant regions for classification based on the last layer features of the global branch. The detailed extraction branch then assesses whether the magnified regions correspond to the lesion area. Finally, a feature consistency constraint between the global and detail branches ensures that the global branch focuses on the appropriate region and extracts sufficient discriminative features for final identification. These focused discriminative features can facilitate the discovery of novel prognostic tumor markers, from the perspective of feature uniqueness and tissue spatial distribution. Extensive experiment results demonstrate that the proposed framework can rapidly deliver accurate and explainable results for pathological grading and prognosis tasks.

Nonuniform thermal behavior in lithium-ion battery packs can accelerate aging, leading to inconsistent cell performance. If not adequately monitored and managed, this heating can give rise to unwanted side reactions, fires, and explosions, underscoring the criticality of temperature field reconstruction. In recent years, data-driven methods have gained popularity for addressing the temperature field reconstruction problem. However, many existing data-driven approaches require retraining when system parameters change, such as the initial temperature distribution or working conditions. This article presents a deep transfer operator learning method named physics-informed adversarial networks. The model architecture incorporates transformer blocks to capture comprehensive time and space features. Additionally, to enhance interpretability and generalization, the model introduces two effective mechanisms: 1) the integration of thermal partial differential equations to ensure compliance with physical laws; and 2) the application of domain adversarial mechanism in transfer learning to extract domain-invariant feature representations. These mechanisms enable the model to effectively reconstruct the temperature field, even in unencountered scenarios during training. The proposed method is validated under real-world energy storage working conditions, demonstrating superior performance compared to state-of-the-art deep learning methods. Notably, the approach exhibits excellent performance even when confronted with the limited availability of training data.

Deep learning with noisy labels is challenging and inevitable in many circumstances. Existing methods reduce the impact of mislabeled samples by reducing loss weights or screening, which highly rely on the model's superior discriminative power for identifying mislabeled samples. However, in the training stage, the trainee model is imperfect and will wrongly predict some mislabeled samples, which cause continuous damage to the model training. Consequently, there is a large performance gap between existing anti-noise models trained with noisy samples and models trained with clean samples. In this paper, we put forward a Gradient Switching Strategy (GSS) to prevent the continuous damage of mislabeled samples to the classifier. Theoretical analysis shows that the damage comes from the misleading gradient direction computed from the mislabeled samples. The trainee model will deviate from the correct optimization direction under the influence of the accumulated misleading gradient of mislabeled samples. To address this problem, the proposed GSS alleviates the damage by switching the gradient direction of each sample based on the gradient direction pool, which contains all-class gradient directions with different probabilities. During training, each gradient direction pool is updated iteratively, which assigns higher probabilities to potential principal directions for high-confidence samples. Conversely, uncertain samples are forced to explore in different directions rather than mislead model in a fixed direction. Extensive experiments show that GSS can achieve comparable performance with a model trained with clean data. Moreover, the proposed GSS is pluggable for existing frameworks. This idea of switching gradient directions provides a new perspective for future noisy-label learning.

Face clustering is a critical task in computer vision due to the increasing number of applications such as augmented reality or photo album management. The primary challenge in this task arises from the imperfections in image feature representations. Given image features extracted from an existing pre-trained representation model, it remains an unresolved problem that how to leverage the inherent characteristics of similarities among unlabelled images to improve the clustering performance. In order to solve face clustering in an unsupervised manner , we develop an effective and robust framework named as Adapt-Infomap. First, we reformulate face clustering as a process of non-overlapping community detection. Specially, Adapt-Infomap achieves face clustering by minimizing the entropy of information flows (also known as the map equation) on an affinity graph of images. Since the affinity graph of images might contain noisy edges, we develop an outlier detection strategy in Adapt-Infomap to adaptively refine the affinity graph. Experiments with ablation studies demonstrate that Adapt-Infomap significantly outperforms existing methods and achieves new state-of-the-arts on three popular large-scale datasets for face clustering, e.g. , an absolute improvement of more than 10 % and 3 % comparing with prior unsupervised and supervised methods respectively in terms of average of Pairwise F-score.

Recently, Convolutional Neural Network (CNN) has achieved excellent performance in the classification task. It is widely known that CNN is deemed as a 'blackbox', which is hard for understanding the prediction mechanism and debugging the wrong prediction. Some model debugging and explanation works are developed for solving the above drawbacks. However, those methods focus on explanation and diagnosing possible causes for model prediction, based on which the researchers handle the following optimization of models manually. In this paper, we propose the first completely automatic model diagnosing and treating tool, termed as Model Doctor. Based on two discoveries that 1) each category is only correlated with sparse and specific convolution kernels, and 2) adversarial samples are isolated while normal samples are successive in the feature space, a simple aggregate gradient constraint is devised for effectively diagnosing and optimizing CNN classifiers. The aggregate gradient strategy is a versatile module for mainstream CNN classifiers. Extensive experiments demonstrate that the proposed Model Doctor applies to all existing CNN classifiers, and improves the accuracy of 16 mainstream CNN classifiers by 1%~5%.

Clinically, the pathological images are intuitive for cancer diagnosis and have been considered as the ‘gold standard’. There are two challenges for applying deep learning into the pathological images analysis: the ultra-large size and the noisy annotations. A pathological image usually contains billions of pixels, which is unsuitable for normal classification models. Furthermore, the ultra-large size and mixed cancerous cells compel the doctor to draw rough boundaries of lesion area according to the cancerous level, which brings two kinds of noisy labels: space noise (annotating inaccurate scope of cancerous area) and level noise (annotating inaccurate cancerous level). Based on the above findings, we propose the space and level cooperation framework, comprising a space-aware branch and a level-aware branch, for pathological cancer grading with noisy annotations. The space-aware branch first turns the ultra-large image into a Multilayer Superpixel (MS) graph, significantly reducing the size and preserving the global features. Then, a global-to-local rectifying strategy is adopted to solve the space noise. The level-aware branch adopts different grouped kernels and a novel grading loss function to handle level noise. Mean-while, two branches cooperate through complementing missing features of each other for handling the above two challenges. Extensive experiments demonstrate that with noisy annotations, the proposed framework achieves SOTA performance on our HCC dataset and two public datasets.

In this paper, we propose a generic approach for accelerating the convergence of existing algorithms to solve the problem of stochastic zeroth-order convex optimization (SZCO). Standard techniques for accelerating the convergence of stochastic zeroth-order algorithms are by exploring multiple functional evaluations (e.g., two-point evaluations), or by exploiting global conditions of the problem (e.g., smoothness and strong convexity). Nevertheless, these classic acceleration techniques are necessarily restricting the applicability of newly developed algorithms. The key of our proposed generic approach is to explore a local growth condition (or called local error bound condition) of the objective function in SZCO. The benefits of the proposed acceleration technique are: (i) it is applicable to both settings with one-point evaluation and two-point evaluations; (ii) it does not necessarily require strong convexity or smoothness condition of the objective function; (iii) it yields an improvement on convergence for a broad family of problems. Empirical studies in various settings demonstrate the effectiveness of the proposed acceleration approach.

In linear stochastic bandits, it is commonly assumed that payoffs are with sub-Gaussian noises. In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite moments of order $1+\epsilon$, for some $\epsilon\in (0,1]$. We rigorously analyze the regret lower bound of LinBET as $\Omega(T^{\frac{1}{1+\epsilon}})$, implying that finite moments of order 2 (i.e., finite variances) yield the bound of $\Omega(\sqrt{T})$, with $T$ being the total number of rounds to play bandits. The provided lower bound also indicates that the state-of-the-art algorithms for LinBET are far from optimal. By adopting median of means with a well-designed allocation of decisions and truncation based on historical information, we develop two novel bandit algorithms, where the regret upper bounds match the lower bound up to polylogarithmic factors. To the best of our knowledge, we are the first to solve LinBET optimally in the sense of the polynomial order on $T$. Our proposed algorithms are evaluated based on synthetic datasets, and outperform the state-of-the-art results.

Contextual bandits with linear payoffs, which are also known as linear bandits, provide a powerful alternative for solving practical problems of sequential decisions, e.g., online advertisements. In the era of big data, contextual data usually tend to be high-dimensional, which leads to new challenges for traditional linear bandits mostly designed for the setting of low-dimensional contextual data. Due to the curse of dimensionality, there are two challenges in most of the current bandit algorithms: the first is high time-complexity; and the second is extreme large upper regret bounds with high-dimensional data. In this paper, in order to attack the above two challenges effectively, we develop an algorithm of Contextual Bandits via RAndom Projection (CBRAP) in the setting of linear payoffs, which works especially for high-dimensional contextual data. The proposed CBRAP algorithm is time-efficient and flexible, because it enables players to choose an arm in a low-dimensional space, and relaxes the sparsity assumption of constant number of non-zero components in previous work. Besides, we prove an upper regret bound for the proposed algorithm, which is associated with reduced dimensions. By comparing with three benchmark algorithms, we demonstrate improved performance on cumulative payoffs of CBRAP during its sequential decisions on both synthetic and real-world datasets, as well as its superior time-efficiency.

Best arm identification in stochastic Multi-Armed Bandits (MAB) has become an essential variant in the research line of bandits for decision-making problems. In previous work, the best arm usually refers to an arm with the highest expected payoff in a given decision-arm set. However, in many practical scenarios, it would be more important and desirable to incorporate the risk of an arm into the best decision. In this paper, motivated by practical applications with risk via bandits, we investigate the problem of Risk Control of Best Arm Identification (RCBAI) in stochastic MAB. Based on the technique of Successive Rejects (SR), we show that the error resulting from the mean-variance estimation is sub-Gamma by setting mild assumptions on stochastic payoffs of arms. Besides, we develop an algorithm named as RCMAB. SR, and derive an upper bound for the probability of error for RCBAI in stochastic MAB. We demonstrate the superiority of the RCMAB. SR algorithm in synthetic datasets, and then apply the RCMAB. SR algorithm in financial data for yearly investments to show its superiority for practical applications.

Secure localization has become very important in wireless sensor networks. However, the conventional secure localization algorithms used in wireless sensor networks cannot deal with internal attacks and cannot identify malicious nodes. In this paper, a localization based on trust valuation, which can overcome a various attack types, such as spoofing attacks and Sybil attacks, is presented. The trust valuation is obtained via selection of the property set, which includes estimated distance, localization performance, position information of beacon nodes, and transmission time, and discussion of the threshold in the property set. In addition, the robustness of the proposed model is verified by analysis of attack intensity, localization error, and trust relationship for three typical scenes. The experimental results have shown that the proposed model is superior to the traditional secure localization models in terms of malicious nodes identification and performance improvement.

Online dictionary learning for sparse coding is an effective tool for data analysis. It incrementally learns a set of basis vectors with sparse linear combinations of these vectors when new samples appear. Previous work assumes that the samples embed Gaussian noises, which weaken the power of these methods in handling real applications with non-negative data (e.g., frequency data in word counts). Differently, in this paper, we concentrate on online learning for non-negative dictionary by using moment information for sparse Poisson coding. We exploit the non-negativity of Poisson models to learn a set of non-negative basis vectors and a non-negative sparse linear combination for the moment information of samples. Specifically, we first formulate the online learning problem via the maximum-a-posteriori (MAP) framework. We then propose a novel online algorithm which alternatively updates the sparse-coefficient vector and the basis vectors with non-negativity constraints when a new sample arrives. More importantly, we present sufficient convergence analyses to guarantee the performance of the proposed algorithm, which leads to convergence of a stable dictionary for characterizing the moment information of samples. We finally conduct a series of experiments on word-counts data and image data to show merits of the proposed online algorithm.

Zhang neural network (ZNN) is a novel class of recurrent neural network with superior solution ability and convergence performance. For real-time solution of Moore-Penrose pseudoinverses of time-varying matrices based on continuous-time recurrent neural network, this paper proposes three different ZNN models, each of which is derived from a specifically-chosen Zhang function (ZF). Theoretical analyses guarantee the global convergence of the three different ZNN models and their fast convergence rate. Besides, the proposed ZNN models show additional great advantages when used to deal with matrices with contrasting numbers of rows and columns. Computer simulations and experiments further verify the theoretical results, vividly demonstrating the effectiveness and efficiency of the proposed ZNN models.