Data augmentation is an intuitive solution to increase the diversity of training instances in the machine learning community. Mixup is acknowledged as an effective and efficient mix-based data augmentation method, following a linear alignment assumption that the linear interpolations of features align the corresponding linear interpolations of labels. Unfortunately, this assumption can be violated in many complex scenarios, resulting in augmented instances with noisy labels, especially for regression problems. To solve this problem, we propose an easy-to-implement mixup method, namely DEnosing MIXUP (DE-mixup), which iteratively corrects the noisy response targets by leveraging an auxiliary noise estimation task with mixup deep features. Additionally, we suggest an efficient optimization method with alternating direction method of multipliers. We compare DE-mixup with the existing mixup variants and other prevalent data augmentation methods across benchmark regression datasets. Empirical results indicate the effectiveness of DE-mixup under the in-distribution and out-of-distribution cases.

Unsupervised domain adaptive hashing has emerged as a promising approach for efficient and memory-friendly cross-domain retrieval. It leverages the model learned on labeled source domains to generate compact binary codes for unlabeled target domain samples, ensuring that semantically similar samples are mapped to nearby points in the Hamming space. Existing methods typically apply domain adaptation techniques to the feature space or the Hamming space, especially pseudo-labeling and feature alignment. However, the inherent noise of pseudo-labels and the insufficient exploration of complementary knowledge across spaces hinder the ability of the adapted model. To address these challenges, we propose a Vision-language model assisted Pseudo-labeling and Dual Space adaptation (VPDS) method. Motivated by the strong zero-shot generalization capabilities of pre-trained vision-language models (VLMs), VPDS leverages VLMs to calibrate pseudo-labels, thereby mitigating pseudo-label bias. Furthermore, to simultaneously utilize the semantic richness of high-dimensional feature space and preserve discriminative efficiency of low-dimensional Hamming space, we introduce a dual space adaptation approach that performs independent alignment within each space. Extensive experiments on three benchmark datasets demonstrate that VPDS consistently outperforms existing methods in both cross-domain and single-domain retrieval tasks, highlighting its effectiveness and superiority.

Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This article introducesVulnSense, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem.VulnSenselearns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically,VulnSenselearns from three main resources: 1) seen classes with labeled code instances; 2) descriptions of these seen classes; and 3) descriptions of “unseen” classes which have no labeled instances. Our experiments underscoreVulnSense's superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities.VulnSensedemonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work.

The generalized arc consistency (GAC) algorithm is the prevailing solution for alldifferent constraint problems. The core part of GAC for alldifferent constraints is excavating and enumerating all the strongly connected components (SCCs) of the graph model. This causes a large amount of complex data structures to maintain the node information, leading to a large overhead both in time and memory space. More critically, the complexity of the data structures further precludes the coordination of different optimization schemes for GAC. To solve this problem, the key observation of this paper is that the GAC algorithm only cares whether a node of the graph model is in an SCC or not, rather than which SCCs it belongs to. Based on this observation, we propose AllDiffbit, which employs bitwise data structures and operations to efficiently determine if a node is in an SCC. This greatly reduces the corresponding overhead, and enhances the ability to incorporate existing optimizations to work in a synergistic way. Our experiments show that AllDiffbit outperforms the state-of-the-art GAC algorithms over 60%.

AllDifferent constraint is widely used in Constraint Programming to model real world problems. Existing Generalized Arc Consistency (GAC) algorithms map an AllDifferent constraint onto a bipartite graph and utilize the structure of Strongly Connected Components (SCCs) in the graph to filter values. Calculating SCCs is time-consuming in the existing algorithms, so we propose a novel GAC algorithm for AllDifferent constraint in this paper, which eliminates the computation of SCCs. We prove that all redundant edges in the bipartite graph point to some alternating cycles. Our algorithm exploits this property and uses a more efficient method to filter values, which is based on breadth-first search. Experimental results on the XCSP3 benchmark suite show that our algorithm considerably outperforms the state-of-the-art GAC algorithms.

Feature Selection (FS) is a significant data preprocessing technique, whose purpose is to identify feature subset that can improve the prediction accuracy from the subsequent training model, while ensuring that the number of features is minimized. The Binary Golden Eagle Optimizer (BGEO) algorithm can efficiently search for the feature subset that satisfies the desired requirements on small and medium sized data. However, searching for subsets becomes much more difficult as the data dimension increases. To handle this problem, we present the Binary Golden Eagle Optimizer algorithm combined with Initialization of Feature Number Subspace (BGEO-IFNS) as the first application of BGEO for high-dimensional FS. Initialization of Feature Number Subspace (IFNS) consists of the following steps: First, the feature space is divided into several subspaces with different feature numbers. Next, new individuals are generated to correspond to the different subspaces. Finally, the quality of these new individuals is assessed using the original population. The initial population generated by this method improves the diversity while maintaining high quality, thus improving solving ability of the subsequent algorithm on high-dimensional data. To validate our approach, we conduct experiments on 14 small and medium dimensional datasets as well as 10 high-dimensional datasets. The experimental results show that BGEO-IFNS achieves a large improvement in effectiveness over BGEO and other state-of-the-art algorithms on the majority of datasets. In addition, BGEO-IFNS achieves optimal performance when compared with other metaheuristic algorithms utilizing IFNS. The results further validate the generalizability and adaptability of the new initialization method with BGEO.

Variable ordering heuristics play a central role in solving constraint satisfaction problems. In this paper, we propose failure based variable ordering heuristics. Following the fail first principle, the new heuristics use two aspects of failure information collected during search. The failure rate heuristics consider the failure proportion after the propagations of assignments of variables and the failure length heuristics consider the length of failures, which is the number of fixed variables composing a failure. We performed a vast experiments in 41 problems with 1876 MiniZinc instances. The results show that the failure based heuristics outperform the existing ones including activity-based search, conflict history search, the refined weighted degree and correlation-based search. They can be new candidates of general purpose variable ordering heuristics for black-box CSP solvers.

Simple Tabular Reduction algorithms (STR) work well to establish Generalized Arc Consistency (GAC) on positive table constraints. However, the existing STR algorithms are useless for negative table constraints. In this work, we propose a novel STR algorithm and its improvement, which work on negative table constraints. Our preliminary experiments are performed on some random instances and a certain benchmark instances. The results show that the new algorithms outperform GAC-valid and the MDD-based GAC algorithm.

Filtering techniques are essential in the search algorithms solving constraint satisfaction problems (CSPs). Arc consistency (AC) is the most often used filtering technique because it cheaply removes some values that cannot belong to any solutions. Comparing with AC, max-Restricted Path Consistency (maxRPC) has a stronger pruning power while it is not suited for use during search because of the prohibitive time cost. Thus, light maxRPC which is the light version of maxRPC was proposed. Comparing with maxRPC, it has a lower time cost and the search algorithm maintaining light maxRPC (MlmaxRPC) can outperform the search algorithm maintaining AC (MAC) on some problems. However, MlmaxRPC suffers from the time waste in the cases that applying a stricter checking standard does not intrigue any value deletion. In order to avoid the time waste in MlmaxRPC, in this paper, partial maxRPC which is a new approximation of maxRPC is proposed. It only applies the stricter checking standard when the value deletion is of high possibility. MpmaxRPC which is the search algorithm maintaining partial maxRPC has a better average performance than MAC and MlmaxRPC.

Maintaining local consistencies can improve the efficiencies of the search algorithms solving constraint satisfaction problems (CSPs). Comparing with arc consistency which is the most widely used local consistency, stronger local consistencies can make the search space smaller while they require higher computational cost. In this paper, we make an attempt on the compromise between the pruning ability and the computational cost. A new local consistency called singleton strong bound consistency (SSBC) and its light version, light SSBC, are proposed. The search algorithm maintaining light SSBC can outperform MAC on a considerable number of problems.

Model-based diagnosis (MBD) uses an abstraction of system to diagnose possible faulty functions of an underlying system. To improve the solution efficiency for multi-fault diagnosis problems, especially for large scale systems, this paper proposes a method to induce reasonable diagnosis solutions, under coarse diagnosis, by using the relationships between system outputs and components. Compared to existing diagnosis methods, the proposed framework only needs to consider associations between outputs and components by using an assumption-based truth maintenance system (ATMS) [de Kleer 1986] to obtain correlation components for every output node. As a result, our method significantly reduces the number of variables required for model diagnosis, which makes it suitable for large scale circuit systems.