Meta-learning for Bayesian optimization accelerates optimization by leveraging knowledge from previous tasks, but existing methods optimize for average performance and fail on challenging outlier tasks critical in practice. These limitations become particularly severe when target tasks exhibit distribution shifts or when optimization budgets are limited in real-world applications. We introduce MetaGameBO, a hierarchical game-theoretic framework that formulates meta-learning as robust optimization through CVaR-based task selection and diversity-aware sample learning. Our approach incorporates uncertainty-aware adaptation via probabilistic embeddings and Thompson sampling for robust generalization to out-of-distribution targets. We establish theoretical guarantees including convergence to game-theoretic equilibria and improved sample complexity, and demonstrate substantial improvements with 95.7% reduction in average loss and 88.6% lower tail risk compared to state-of-the-art methods on challenging tasks and distribution shifts.

Recently, based on multi-view stereo (MVS) methods, utilizing stereo prior information to guide novel-view synthesis has become an important approach to addressing the generalization problem of neural radiance fields (NeRF). However, this approach faces challenges in handling certain difficult scenarios, such as weak texture regions, where it struggles to effectively extract geometric features information. As a result, it encounters limitations in stereo image feature representation and inaccuracies in prior depth estimation. To tackle these problems, we propose the first generalizable novel-view synthesis method that jointly optimizes structured light and NeRF. Considering that active stereo methods based on structured light optimization can enhance geometric feature extraction capability in weak texture regions through the addition of a texture layer, we integrate active stereo vision into novel-view synthesis. To this end, we propose a novel framework, dubbed SLNeRF. First, we design a structured light generation scheme based on Fourier transform and establish a differentiable imaging model using geometric optics and the Lambertian model to generate active stereo images. Then, we obtain stereo image features, as well as prior depth information through the feature extractor, which are used to construct 3D feature volumes. Finally, we accomplish the novel-view synthesis task through a neural renderer. Compared to state-of-the-art generalizable NeRF methods, our method reports encouraging results on public datasets as well as in real-world scenarios.

Neural processes (NPs) are a promising paradigm to enable skill transfer learning across tasks with the aid of the distribution of functions. The previous NPs employ the empirical risk minimization principle in optimization. However, the fast adaption ability to different tasks can vary widely, and the worst fast adaptation can be catastrophic in risk-sensitive tasks. To achieve robust neural processes modeling, we consider the problem of training models in a risk-averse manner, which can control the worst fast adaption cases at a certain probabilistic level. By transferring the risk minimization problem to a two-level finite sum minimax optimization problem, we can easily solve it via a double-looped stochastic mirror prox algorithm with a task-aware variance reduction mechanism via sampling samples across all tasks. The mirror prox technique ensures better handling of complex constraint sets and non-Euclidean geometries, making the optimization adaptable to various tasks. The final solution, by aggregating prox points with the adaptive learning rates, enables a stable and high-quality output. The proposed learning strategy can work with various NPs flexibly and achieves less biased approximation with a theoretical guarantee. To illustrate the superiority of the proposed model, we perform experiments on both synthetic and real-world data, and the results demonstrate that our approach not only helps to achieve more accurate performance but also improves model robustness.

Neural Processes (NPs) combine the adaptability of neural networks with the efficiency of meta-learning, offering a powerful framework for modeling stochastic processes. However, existing methods focus on empirical performance while lacking a rigorous theoretical understanding of generalization. To address this, we propose an information-theoretic framework to analyze the generalization bounds of NPs, introducing dynamical stability regularization to minimize sharpness and improve optimization dynamics. Additionally, we show how noise-injected parameter updates complement this regularization. The proposed approach, applicable to a wide range of NP models, is validated through experiments on classic benchmarks, including 1D regression, image completion, Bayesian optimization, and contextual bandits. The results demonstrate tighter generalization bounds and superior predictive performance, establishing a principled foundation for advancing generalizable NP models.

Computer-aided prohibited item detection is applied in X-ray security inspection to maintain public safety. However, existing prohibited item detectors are limited to a small set of categories in current X-ray datasets, posing potential risks to public security. Since constructing bigger datasets and annotating hundreds of categories is time-consuming and labor-intensive, scaling detectors to more categories with minimal supervision is of great importance. To this end, in this paper, we adopt an open-vocabulary object detection (OVOD) method to detect arbitrary unlabeled novel categories of prohibited item. OVOD methods typically rely on datasets with caption annotations, which are lacking in the domain of prohibited item detection. To support the research on OVOD in X-ray security inspection scenarios, we contribute PIXray Caption dataset, the first X-ray dataset with image-caption pair annotations, which could benchmark and facilitate researches in the community. Further, we propose a novel Open-Vocabulary Prohibited Item Detection (OVPID) network to leverage textual information from captions. OVPID contains two core modules, i.e., Interference Resistant Module (IRM) and Prediction Module (PM). Specifically, IRM includes two submodules, namely Edge Perception (EP) and Foreground Activation (FA), which are designed to address the dilemma of interference caused by overlapping problem and complex background in X-ray images. PM consists of two branches for classification and localization. In classification branch, PM generates more accurate prompts for X-ray dataset via large multimodal model (LMM). In localization branch, PM aligns the student embeddings with both teacher and caption embeddings. Extensive experiments on PIXray Caption dataset demonstrate that OVPID outperforms other OVOD methods by delivering a higher accuracy on novel categories.

Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an anti-overlapping detection transformer (AO-DETR) based on one of the state-of-the-art (SOTA) general object detectors, DETR with improved denoising anchor boxes (DINO). Specifically, to address the feature coupling issue caused by overlapping phenomena, we introduce the category-specific one-to-one assignment (CSA) strategy to constrain category-specific object queries in predicting prohibited items of fixed categories, which can enhance their ability to extract features specific to prohibited items of a particular category from the overlapping foreground-background features. To address the edge blurring problem caused by overlapping phenomena, we propose the look forward densely (LFD) scheme, which improves the localization accuracy of reference boxes in mid-to-high-level decoder layers and enhances the ability to locate blurry edges of the final layer. Similar to DINO, our AO-DETR provides two different versions with distinct backbones, tailored to meet diverse application requirements. Extensive experiments on the PIXray, OPIXray, and HIXray datasets demonstrate that the proposed method surpasses the SOTA object detectors, indicating its potential applications in the field of prohibited item detection. The source code will be available at: https://github.com/Limingyuan001/AO-DETR.

Combining multiple source information can often lead to improved performance on the learning task. Information from different sources could potentially compensate the missing information in a single source. However, designing an effective combining scheme is not always straightforward in practice. This paper aims to combine information from multiple social media websites to enhance the co-clustering performance of two types of objects (social media objects and users) in one social network, since users could leave footprints across different social media websites, such as Twitter, Foursquare, etc. Data generated from multiple heterogeneous sources can be casted in a multi-view setting. Specifically, we construct the relationship matrix as relationship view and features of each individual object from different sources as different feature views. In previous works, features besides relationship matrix were added to co-clustering in the following manners: different features are taken indiscriminately, those features act as hard constraints to force final co-clusters agree with these constraints. A co-regularized collaborative co-clustering model (Co-CoClust) is proposed to simultaneously perform co-clustering on relationship view and clustering on multiple feature views. In this framework, features from different sources are treated discriminately since they are divided into separate views and utilized based on the distance from relationship matrix. Co-regularization technique is introduced to impose a common constraint between co-clustering and clusterings such that the relationship matrix and feature matrix are unified. By alternating minimization, results of co-clustering and clustering from different views are iteratively optimized. Therefore, co-clustering results are improved by leveraging multiple source information. The proposed algorithm proves its effectiveness in social media datasets and traditional document-word datasets.

Abstract Nowadays, the message diffusion links among users or Web sites drive the development of countless innovative applications. However, in reality, it is easier for us to observe the time stamps when different nodes in the network react on a message, while the connections empowering the diffusion of the message remain hidden. This motivates recent extensive studies on thenetwork inference problem: unveiling the edges from the records of messages disseminated through them. Existing solutions are computationally expensive, which motivates us to develop an efficient two-step general framework,Clustering Embedded Network Inference(CENI). CENI integrates clustering strategies to improve the efficiency of network inference. By clustering nodes directly on the time lines of messages, we propose two naive implementations of CENI:Infection-centric CENIandCascade-centric CENI. Additionally, we point out thecritical dimensionproblem of CENI: Instead of one-dimensional time lines, we need to first project the nodes to an Euclidean space of certain dimension before clustering. A CENI adopting clustering method on the projected space can better preserve the structure hidden in the cascades and generate more accurately inferred links. By addressing the critical dimension problem, we propose the third implementation of the CENI framework:Projection-based CENI. Through extensive experiments on two real datasets, we show that the three CENI models only need around 20–50 % of the running time of state-of-the-art methods. Moreover, the inferred edges of Projection-based CENI preserve or even outperform the effectiveness of state-of-the-art methods.

The connection between online users is the key to the success of many important applications, such as viral marketing. In reality, we often easily observe the time when each user in the network receives a message, yet the users' connections that empower the message diffusion remain hidden. Therefore, given the traces of disseminated messages, recent research has extensively studied approaches to uncover the underlying diffusion network. Since topic related information could assist the network inference, previous methods incorporated either users' preferences over topics or the topic distributions of cascading messages. However, methods combining both of them may lead to more accurate results, because they consider a more comprehensive range of available information. In this paper, we investigate this possibility by exploring two principled methods: Weighted Topic Cascade (WTC) and Preference-enhanced Topic Cascade (PTC). WTC and PTC formulate the network inference task as non-smooth convex optimization problems and adopt coordinate proximal gradient descent to solve them. Based on synthetic and real datasets, substantial experiments demonstrate that although WTC is better than several previous approaches in most cases, it is less stable than PTC, which constantly outperforms other baselines with an improvement of 4%∼10% in terms of the F-measure of inferred networks.

As viral marketing in online social networks flourishes recently, a lot of attention has been drawn to the study of influence maximization in social networks. However, most works in influence maximization have overlooked the important role that social network providers (websites) play in the diffusion processes. Viral marketing campaigns are usually sold by websites as services to their clients. The websites can not only select initial sets of users to start diffusion processes, but can also have impacts throughout the diffusion processes by deciding when the information should be brought to the attention of individual users. This is especially true when user attention is limited, and the websites have to notify users about an item to bring it into the attention of users. In this paper, we study the diffusion of information from the perspective of social network websites. We propose a novel push-driven cascade (PDC) model, which emphasizes the role of websites during the diffusion of information. In the PDC model, the website "pushes" items to bring them to the attention of users, and whether a user is interested in an item is decided by her preference and the social influence from her friends. Analogous to the influence maximization problem on the traditional information diffusion models, we propose a dynamic influence maximization problem on the PDC model, which is defined as a sequential decision making problem for the website. We show that the problem can be formalized as a Markov sequential decision problem, and there exists a deterministic Markovian policy that is an optimal solution for the problem. We develop an AO algorithm that finds the optimal solution for the problem, and a heuristic online search algorithm, which has similar effectiveness, but is significantly more efficient. We evaluate the proposed algorithms on various real-world datasets, and find them significantly outperform the baselines.

We propose a robust tracking algorithm based on local sparse coding with discriminative dictionary learning and new keypoint matching schema. This algorithm consists of two parts: the local sparse coding with online updated discriminative dictionary for tracking (SOD part), and the keypoint matching refinement for enhancing the tracking performance (KP part). In the SOD part, the local image patches of the target object and background are represented by their sparse codes using an over-complete discriminative dictionary. Such discriminative dictionary, which encodes the information of both the foreground and the background, may provide more discriminative power. Furthermore, in order to adapt the dictionary to the variation of the foreground and background during the tracking, an online learning method is employed to update the dictionary. The KP part utilizes refined keypoint matching schema to improve the performance of the SOD. With the help of sparse representation and online updated discriminative dictionary, the KP part are more robust than the traditional method to reject the incorrect matches and eliminate the outliers. The proposed method is embedded into a Bayesian inference framework for visual tracking. Experimental results on several challenging video sequences demonstrate the effectiveness and robustness of our approach.

With the effect of word-of-the-mouth, trends in social networks are now playing a significant role in shaping people's lives. Predicting dynamic trends is an important problem with many useful applications. There are three dynamic characteristics of a trend that should be captured by a trend model: intensity, coverage and duration. However, existing approaches on the information diffusion are not capable of capturing these three characteristics. In this paper, we study the problem of predicting dynamic trends in social networks. We first define related concepts to quantify the dynamic characteristics of trends in social networks, and formalize the problem of trend prediction. We then propose a Dynamic Activeness (DA) model based on the novel concept of activeness, and design a trend prediction algorithm using the DA model. We examine the prediction algorithm on the DBLP network, and show that it is more accurate than state-of-the-art approaches.

Keeping silence widely exists in human society and has been studied in social science for a long time. Similar to real social networks, in online social networks, after observing an event from their friends, users may not decide whether to share it at once due to different reasons. In influence prop

Learning of the information diffusion model is a fundamental problem in the study of information diffusion in social networks. Existing approaches learn the diffusion models from events in social networks. However, events in social networks may have different underlying reasons. Some of them may be caused by the social influence inside the network, while others may reflect external trends in the ``real world''. Most existing work on the learning of diffusion models does not distinguish the events caused by the social influence from those caused by external trends.

Online reviews play a crucial role in today's electronic commerce. It is desirable for a customer to read reviews of products or stores before making the decision of what or from where to buy. Due to the pervasive spam reviews, customers can be misled to buy low-quality products, while decent stores can be defamed by malicious reviews. We observe that, in reality, a great portion (> 90% in the data we study) of the reviewers write only one review (singleton review). These reviews are so enormous in number that they can almost determine a store's rating and impression. However, existing methods did not examine this larger part of the reviews. Are most of these singleton reviews truthful ones? If not, how to detect spam reviews in singleton reviews? We call this problem singleton review spam detection.

The problem of maximizing influence spread has been widely studied in social networks, because of its tremendous number of applications in determining critical points in a social network for information dissemination. All the techniques proposed in the literature are inherently static in nature, which are designed for social networks with a fixed set of links. However, many forms of social interactions are transient in nature, with relatively short periods of interaction. Any influence spread may happen only during the period of interaction, and the probability of spread is a function of the corresponding interaction time. Furthermore, such interactions are quite fluid and evolving, as a result of which the topology of the underlying network may change rapidly, as new interactions form and others terminate. In such cases, it may be desirable to determine the influential nodes based on the dynamic interaction patterns. Alternatively, one may wish to discover the most likely starting points for a given infection pattern. We will propose methods which can be used both for optimization of information spread, as well as the backward tracing of the source of influence spread. We will present experimental results illustrating the effectiveness of our approach on a number of real data sets.

This paper presents a method which combined radon transform with machine learning technology for electronic component orientation and identification in product line scenes. This method can fetch electronic components' positions and yawing angles and enables the full automation of electronic product line. Firstly, it take images contain a single electronic component as training samples and retrieve its features. Secondly, it uses thresholds to segment objects in overlapping status. Finally, it use radon transform to detect the axis of object and then according to the component features acquired from training sample and classifier, the algorithm can identify electronic component pin's orientation. To increase the method's detection accuracy and speed in factory product line environment, this paper also proposed a strategy for the combination of the method with mechanism. Experiments show that this method has a perfect performance and completely fulfills the requirements of factory product line environment. This method achieves a recall rate of 81.7% and precision rate of 95.1%, after combined the algorithm with mechanism, the precision rate enhance to 98.5% and detection speed lifting strikingly.