Set Of Queries Research Articles

Adaptive Prototype Interaction Network for Few-Shot Knowledge Graph Completion.

Few-shot knowledge graph completion (FKGC), which aims to infer new triples for a relation using only a few reference triples of the relation, has attracted much attention in recent years. Most existing FKGC methods learn a transferable embedding space, where entity pairs belonging to the same relations are close to each other. In real-world knowledge graphs (KGs), however, some relations may involve multiple semantics, and their entity pairs are not always close due to having different meanings. Hence, the existing FKGC methods may yield suboptimal performance when handling multiple semantic relations in the few-shot scenario. To solve this problem, we propose a new method named adaptive prototype interaction network (APINet) for FKGC. Our model consists of two major components: 1) an interaction attention encoder (InterAE) to capture the underlying relational semantics of entity pairs by modeling the interactive information between head and tail entities and 2) an adaptive prototype net (APNet) to generate relation prototypes adaptive to different query triples by extracting query-relevant reference pairs and reducing the data inconsistency between support and query sets. Experimental results on two public datasets demonstrate that APINet outperforms several state-of-the-art FKGC methods. The ablation study demonstrates the rationality and effectiveness of each component of APINet.

Word vector embedding and self-supplementing network for Generalized Few-shot Semantic Segmentation

Under the condition of sufficient base class samples and a few novel class samples, Generalized Few-shot Semantic Segmentation (GFSS) classifies each pixel in the query image as base class, novel class, or background. A standard GFSS approach involves two training stages: base class learning and novel class updating. However, inter-class interference and information loss which contribute to the poor performance of GFSS, have not been synthetical considered. To address the problem, we propose an Embedded-Self-Supplementing Network (ESSNet), i.e., semantic word embedding and query set self-supplementing information to enhance segmentation accuracy. Specifically, the semantic word embedding module employs distance information between word vectors to assist the model in learning the distance between class prototypes. In order to transform the semantic word vector prototypes from the semantic space to the visual embedding space, we designed a triplet loss function to supervise the word vector embedding module, where the word vector prototype serves as an anchor and positive-negative samples are collected among the general features of the support image. To compensate for the information loss caused by using prototypes to represent classes, we propose a self-supplementing module to mine the information contained in the query image. Specifically, this module first makes a preliminary prediction on the query image, then selects high-confidence area to form pseudo labels, and finally uses pseudo labels to extract query prototypes to supplement the missing information. Extensive experiments on PASCAL-5i and COCO-20i show that ESSNet has superior performance and outperforms state-of-the-art methods in all settings.

Inference-Based Information Relevance Reasoning Method in Situation Assessment

The growing volume of information available to decision-makers makes it increasingly challenging to process all data during decision-making. As a result, a method for selecting only relevant information is highly desirable. Moreover, since the meaning of information depends on its context, the decision-making process requires mechanisms to identify the context of specific scenarios. In this paper, we propose a conceptual framework that utilizes Situation Theory to formalize the concept of context and analyze information relevance. Building on this framework, we introduce an inference-based reasoning process that automatically identifies the information necessary to characterize a given situation. We evaluate our approach in a cybersecurity scenario where computer agents respond to queries by utilizing available information and sharing relevant facts with other agents. The results show that our method significantly reduces the time required to infer answers to situation-specific queries. Additionally, we demonstrate that using only relevant information provides the same answers as using the entire knowledge base. Finally, we show that the method can be applied to a limited set of training queries, allowing the reuse of relevant facts to address new queries effectively.

Early screening of miliary tuberculosis with tuberculous meningitis based on few-shot learning with multiple windows and feature granularities

Tuberculous meningitis (TBM) is a fatal tuberculosis caused by a large number of Mycobacterium tuberculosis (M. tuberculosis) spread by blood flow, with a case fatality rate of more than 50%. It is one of the most serious complications of miliary tuberculosis (MT), whose incidence is closely related to MT. If doctors can provide early diagnosis and active treatment for TBM, the case fatality rate will be significantly reduced. At present, there is a lack of methods to predict the progression of MT to TBM in clinic. To explore whether MT cases will experience TBM, we propose an early screening model of miliary tuberculosis with tuberculous meningitis (MT-TBM) based on few-shot learning with multiple windows and feature granularities (MWFG). This model aims to screen potential TBM cases through chest computerized tomography (CT) images of MT cases. Chest CT is a routine examination for MT cases. The MWFG module can extract more comprehensive features from a set of CT images of each MT case. The softmax classifier with adaptive regularization is trained on the cooperation of support set and query set, which can effectively prevent overfitting. Experiments on a dataset of 40 MT cases with chest CT images established by the medical records demonstrate that our proposed model achieves state-of-the-art performance in the early screening of MT-TBM. It can establish the connection between MT and MT-TBM through chest CT images of MT cases. The early screening model of MT-TBM based on few-shot learning with MWFG fills the research gap in computer-aided predicting TBM and has certain clinical effects. This research can provide some reference for clinicians in early diagnosis of MT-TBM and help clinicians in the early prevention and treatment of TBM for MT patients.

Similarity joins and clustering for SPARQL

The SPARQL standard provides operators to retrieve exact matches on data, such as graph patterns, filters and grouping. This work proposes and evaluates two new algebraic operators for SPARQL 1.1 that return similarity-based results instead of exact results. First, a similarity join operator is presented, which brings together similar mappings from two sets of solution mappings. Second, a clustering solution modifier is introduced, which instead of grouping solution mappings according to exact values, brings them together by using similarity criteria. For both cases, a variety of algorithms are proposed and analysed, and use-case queries that showcase the relevance and usefulness of the novel operators are presented. For similarity joins, experimental results are provided by comparing different physical operators over a set of real world queries, as well as comparing our implementation to the closest work found in the literature, DBSimJoin, a PostgreSQL extension that supports similarity joins. For clustering, synthetic queries are designed in order to measure the performance of the different algorithms implemented.

Text-aware small sample remote sensing image classification based on contrastive learning

In view of the fact that existing methods mainly use a single modality of remote sensing images to solve the problem of low similarity of the same category, a remote sensing image classification method based on multimodal learning is proposed. Firstly, the spatial features of the image are corrected and the image encoder is pre-trained using contrastive learning to generate image features, and the text encoder is used to generate text features. Secondly, a feature decoder is introduced to obtain text-aware visual features, and a new attention mechanism method is proposed in the feature fusion stage. Then, a new image encoder is designed to improve the classification accuracy. Finally, the similarity between the support set and the query set is calculated to further predict the category. Experiments are conducted on the NWPU-RESISC45, AID, and UC Merced datasets. Its 5-way 5-shot accuracy reaches 86.46%、85.89%and 80.32%outperforms the existing small-sample remote sensing image classification methods, respectively.

Meta-learning for real-world class incremental learning: a transformer-based approach

Modern natural language processing (NLP) state-of-the-art (SoTA) deep learning (DL) models have hundreds of millions of parameters, making them extremely complex. Large datasets are required for training these models, and while pretraining has reduced this requirement, human-labelled datasets are still necessary for fine-tuning. Few-shot learning (FSL) techniques, such as meta-learning, try to train models from smaller datasets to mitigate this cost. However, the tasks used to evaluate these meta-learners frequently diverge from the problems in the real world that they are meant to resolve. This work aims to apply meta-learning to a problem that is more pertinent to the real world: class incremental learning (IL). In this scenario, after completing its training, the model learns to classify newly introduced classes. One unique quality of meta-learners is that they can generalise from a small sample size to classes that have never been seen before, which makes them especially useful for class incremental learning (IL). The method describes how to emulate class IL using proxy new classes. This method allows a meta-learner to complete the task without the need for retraining. To generate predictions, the transformer-based aggregation function in a meta-learner that modifies data from examples across all classes has been proposed. The principal contributions of the model include concurrently considering the entire support and query sets, and prioritising attention to crucial samples, such as the question, to increase the significance of its impact during inference. The outcomes demonstrate that the model surpasses prevailing benchmarks in the industry. Notably, most meta-learners demonstrate significant generalisation in the context of class IL even without specific training for this task. This paper establishes a high-performing baseline for subsequent transformer-based aggregation techniques, thereby emphasising the practical significance of meta-learners in class IL.

Few-shot bearing fault diagnosis method based on an EEMD parallel neural network and a relation network

Bearing fault diagnosis presents challenges, such as insufficient fault samples and significant fault data distribution variation in different bearing operating conditions. These problems cause traditional deep learning models to show poor generality and accuracy during bearing fault diagnosis. To address these challenges, this paper proposed a few-shot bearing fault diagnosis method based on an Ensemble Empirical Mode Decomposition (EEMD) parallel neural network and a relation network (RN). First, the original bearing fault vibration signal was decomposed by EEMD, while the decomposed signal components were processed via Short Time Fourier Transfor (STFT) to obtain a two-dimensional time-frequency feature map. Then, a parallel neural network was used for initial fault feature extraction, after which the extracted features were fused to construct a more accurate multi-dimensional fault feature map. A more precise fault feature vector was generated via the feature embedding module of the RN, and the fault features of the support and query sets were stitched to create a fault feature vector set. Finally, the relation module of the RN was used for the nonlinear distance determination of the fault feature vector set and to generate the relation score for the few-shot variable condition bearing fault diagnosis. In this paper, EEMD module is introduced into RN to construct multi-dimensional fault characteristics of the original fault signal. Original signal decomposition, STFT transformation and splicing effectively improve the randomness and blindness of convolution operations, improve the accuracy of fault feature extraction in RN, and thus improve the overall diagnostic performance of the model. The experimental results showed that the proposed model obtained higher diagnostic accuracy than the matching network (MN) and RN meta-learning fault diagnosis (MLFD) methods. The accuracy of fault diagnosis of the model in 5Way-Nshot is >80%, and the accuracy of fault diagnosis in 5Way-10shot is the highest at 95.2%.

Set of Diverse Queries With Uncertainty Regularization for Composed Image Retrieval

Set of Diverse Queries With Uncertainty Regularization for Composed Image Retrieval

Adaptive Quotient Filters

Filters trade off accuracy for space and occasionally return false positive matches with a bounded error. Numerous systems use filters in fast memory to avoid performing expensive I/Os to slow storage. A fundamental limitation in traditional filters is that they do not change their representation upon seeing a false positive match. Therefore, the maximum false positive rate is only guaranteed for a single query, not for an arbitrary set of queries. We can improve the filter's performance on a stream of queries, especially on a skewed distribution, if we can adapt after encountering false positives. Adaptive filters, such as telescoping quotient filters and adaptive cuckoo filters, update their representation upon detecting a false positive to avoid repeating the same error in the future. Adaptive filters require an auxiliary structure, typically much larger than the main filter and often residing on slow storage, to facilitate adaptation. However, existing adaptive filters are not practical and have not been adopted in real-world systems for two main reasons. First, they offer weak adaptivity guarantees, meaning that fixing a new false positive can cause a previously fixed false positive to come back. Secondly, the sub-optimal design of the auxiliary structure results in adaptivity overheads so substantial that they can actually diminish overall system performance compared to a traditional filter. In this paper, we design and implement the \sysname, the first practical adaptive filter with minimal adaptivity overhead and strong adaptivity guarantees, which means that the performance and false-positive guarantees continue to hold even for adversarial workloads. The \sysname is based on the state-of-the-art quotient filter design and preserves all the critical features of the quotient filter such as cache efficiency and mergeability. Furthermore, we employ a new auxiliary structure design which results in considerably low adaptivity overhead and makes the \sysname practical in real systems. We evaluate the \sysname by using it to filter queries to an on-disk B-tree database and find no negative impact on insert or query performance compared to traditional filters. Against adversarial workloads, the \sysname preserves system performance, whereas traditional filters incur 2× slowdown from adversaries representing as low as 1% of the workload. Finally, we show that on skewed query workloads, the \sysname can reduce the false-positive rate 100× using negligible (1/1000th of a bit per item) space overhead.

Meta-collaboration-based semantic contrast for inductive knowledge representation learning

Inductive knowledge representation learning aims at effectively representing new entities in emerging knowledge graphs based on current ones, providing positive support for reasoning facts with newly emerging entities. It requires a scheme that can derive the instant knowledge to generate rational representations for new entities. Recently, some approaches have been developed for it by capturing logical rules between entities, mining structural information of KGs, or learning multiple structural patterns of entities. However, there are two main challenges that they have yet to overcome. The first is the structural bias-induced semantic ambiguity, where new entities are typically represented in a manner akin to those with analogous structures, during which the identical structures are emphasized while the differences are overlooked. We refer to this as the structural bias, which will lead to the generated representations of new entities being semantically ambiguous. The second is the potential sparsity of new entities. The presence of new entities with low frequencies brings about the insufficient representations for these new entities even training a model from scratch with substantial costs. To this end, we propose a Meta-Collaboration-based Semantic Contrast (MCSC) framework with the aim of addressing both issues above. Following the current meta-task formulation scheme, we first acquire the relation-specific knowledge to produce entity representations through modeling relations as feedback. Then, a multi-layer graph neural network module is developed to aggregate sufficient neighbor information to update entity representations. In the final, a collaborative semantic contrast module is designed on both support and query sets to respectively overcome the structural bias-induced semantic ambiguity and the potential sparsity of new entities challenges. Such a meta-collaboration-based semantic contrast procedure transcends current meta-learning paradigms in inductive knowledge representation learning that fail to learn semantically discriminative entity representations. Experimental results of the inductive link prediction task on 12 benchmark datasets demonstrate the superiority of MCSC over SOTA baselines.

Optimum noise mechanism for differentially private queries in discrete finite sets

The differential privacy (DP) literature often centers on meeting privacy constraints by introducing noise to the query, typically using a pre-specified parametric distribution model with one or two degrees of freedom. However, this emphasis tends to neglect the crucial considerations of response accuracy and utility, especially in the context of categorical or discrete numerical database queries, where the parameters defining the noise distribution are finite and could be chosen optimally. This paper addresses this gap by introducing a novel framework for designing an optimal noise probability mass function (PMF) tailored to discrete and finite query sets. Our approach considers the modulo summation of random noise as the DP mechanism, aiming to present a tractable solution that not only satisfies privacy constraints but also minimizes query distortion. Unlike existing approaches focused solely on meeting privacy constraints, our framework seeks to optimize the noise distribution under an arbitrary (ϵ,δ)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(\\epsilon , \\delta )$$\\end{document} constraint, thereby enhancing the accuracy and utility of the response. We demonstrate that the optimal PMF can be obtained through solving a mixed-integer linear program. Additionally, closed-form solutions for the optimal PMF are provided, minimizing the probability of error for two specific cases. Numerical experiments highlight the superior performance of our proposed optimal mechanisms compared to state-of-the-art methods. This paper contributes to the DP literature by presenting a clear and systematic approach to designing noise mechanisms that not only satisfy privacy requirements but also optimize query distortion. The framework introduced here opens avenues for improved privacy-preserving database queries, offering significant enhancements in response accuracy and utility.

Weighted Contrastive Prototype Network for Few-Shot Hyperspectral Image Classification with Noisy Labels

Few-shot hyperspectral image classification aims to develop the ability of classifying image pixels by using relatively few labeled pixels per class. However, due to the inaccuracy of the localization system and the bias of the ground survey, the potential noisy labels in the training data pose a very significant challenge to few-shot hyperspectral image classification. To solve this problem, this paper proposes a weighted contrastive prototype network (WCPN) for few-shot hyperspectral image classification with noisy labels. WCPN first utilizes a similarity metric to generate the weights of the samples from the same classes, and applies them to calibrate the class prototypes of support and query sets. Then the weighted prototype network will minimize the distance between features and prototypes to train the network. WCPN also incorporates a weighted contrastive regularization function that uses the sample weights as gates to filter the fake positive samples whose labels are incorrect to further improve the discriminative power of the prototypes. We conduct experiments on multiple hyperspectral image datasets with artificially generated noisy labels, and the results show that the WCPN has excellent performance that can sufficiently mitigate the impact of noisy labels.

Improved Discrimination of Mass Spectral Isomers Using the High-Dimensional Consensus Mass Spectral Similarity Algorithm.

This study employs a high-dimensional consensus mass spectral (HDCMS) similarity scoring technique to discriminate isomers collected using an electron ionization mass spectrometer. The HDCMS method was previously introduced and applied to the discrimination of mass spectra of constitutional isomers, methamphetamine and phentermine, collected with direct analysis real-time mass spectrometry (DART-MS). The method formulates the problem of discriminating mass spectra in a mathematical Hilbert space and is hence called "high dimensional." It requires replicate mass spectra to build a Gaussian model and evaluate the inner products between these functions. The resulting measurement variability is used as a signature by which to discriminate spectra. In this work, HDCMS is tested on electron impact ionization (EI) mass spectra of 7 terpene and terpene-related (C10H16 and C10H14) isomers with experimental retention indices that differ by less than 30 and with traditional cosine similarity scores greater than 0.9, on a scale of 0 to 1, when compared with at least one other compound in the test set. Using identical instrument parameters, 15 replicate gas chromatography-electron ionization-mass spectrometry (GC-EI-MS) spectra of each isomer were collected and separated into distinct library and query sets. The HDCMS algorithm discriminated each isomer, indicating the method's potential. Because the method requires replicate measurements, observations from a simple heuristic study of the number of replicates required to discriminate these isomers is presented. The paper concludes with a discussion of compound discrimination using HDCMS and the benefits and drawbacks of applying the method to EI-MS data.

Modelling user notification scenarios in privacy policies

The processing of personal data gives a rise to many privacy concerns, and one of them is to ensure the transparency of data processing to end users. Usually this information is communicated to them using privacy policies. In this paper, the problem of user notification in case of data breaches and policy changes is addressed, besides an ontology-based approach to model them is proposed. To specify the ontology concepts and properties, the requirements and recommendations for the legislative regulations as well as existing privacy policies are evaluated. A set of SPARQL queries to validate the correctness and completeness of the proposed ontology are developed. The proposed approach is applied to evaluate the privacy policies designed by cloud computing providers and IoT device manufacturers. The results of the analysis show that the transparency of user notification scenarios presented in the privacy policies is still very low, and the companies should reconsider the notification mechanisms and provide more detailed information in privacy policies.

Bi-Directional Ensemble Feature Reconstruction Network for Few-Shot Fine-Grained Classification.

The main challenge for fine-grained few-shot image classification is to learn feature representations with higher inter-class and lower intra-class variations, with a mere few labelled samples. Conventional few-shot learning methods however cannot be naively adopted for this fine-grained setting - a quick pilot study reveals that they in fact push for the opposite (i.e., lower inter-class variations and higher intra-class variations). To alleviate this problem, prior works predominately use a support set to reconstruct the query image and then utilize metric learning to determine its category. Upon careful inspection, we further reveal that such unidirectional reconstruction methods only help to increase inter-class variations and are not effective in tackling intra-class variations. In this paper, we introduce a bi-reconstruction mechanism that can simultaneously accommodate for inter-class and intra-class variations. In addition to using the support set to reconstruct the query set for increasing inter-class variations, we further use the query set to reconstruct the support set for reducing intra-class variations. This design effectively helps the model to explore more subtle and discriminative features which is key for the fine-grained problem in hand. Furthermore, we also construct a self-reconstruction module to work alongside the bi-directional module to make the features even more discriminative. We introduce the snapshot ensemble method in the episodic learning strategy - a simple trick to further improve model performance without increasing training costs. Experimental results on three widely used fine-grained image classification datasets, as well as general and cross-domain few-shot image datasets, consistently show considerable improvements compared with other methods.

Cross-attention based dual-similarity network for few-shot learning

Few-shot classification is a challenging task to recognize unseen classes with limited data. Following the success of Vision Transformer in various large-scale datasets image recognition domains, recent few-shot classification methods employ transformer-style. However, most of them focus only on cross-attention between support and query sets, mainly considering channel-similarity. To address this issue, we introduce dual-similarity network (DSN) in which attention maps for the same target within a class are made identical. With the network, a way of effective training through the integration of the channel-similarity and the map-similarity has been sought. Our method, while focused on N-way K-shot scenarios, also demonstrates strong performance in 1-shot settings through augmentation. The experimental results verify the effectiveness of DSN on widely used benchmark datasets.

Reconstruction Attacks on Aggressive Relaxations of Differential Privacy

Differential privacy is a widely accepted formal privacy definition that allows aggregate information about a dataset to be released while controlling privacy leakage for individuals whose records appear in the data. Due to the unavoidable tension between privacy and utility, there have been many works trying to relax the requirements of differential privacy to achieve greater utility.One class of relaxation, which is gaining support outside the privacy community is embodied by the definitions of individual differential privacy (IDP) and bootstrap differential privacy (BDP). Classical differential privacy defines a set of neighboring database pairs and achieves its privacy guarantees by requiring that each pair of neighbors should be nearly indistinguishable to an attacker. The privacy definitions we study, however, aggressively reduce the set of neighboring pairs that are protected.To a non-expert, IDP and BDP can seem very appealing as they echo the same types of privacy explanations that are associated with differential privacy, and also experimentally achieve dramatically better utility. However, we show that they allow a significant portion of the dataset to be reconstructed using algorithms that have arbitrarily low privacy loss under their privacy accounting rules.With the non-expert in mind, we demonstrate these attacks using the preferred mechanisms of these privacy definitions. In particular, we design a set of queries that, when protected by these mechanisms with high noise settings (i.e., with claims of very low privacy loss), yield more precise information about the dataset than if they were not protected at all. The specific attacks here can be defeated and we give examples of countermeasures. However, the defenses are either equivalent to using differential privacy or to ad-hoc methods tailored specifically to the attack (with no guarantee that they protect against other attacks). Thus, the defenses emphasize the deficiencies of these privacy definitions.

Contrastive prototype network with prototype augmentation for few-shot classification

In recent years, metric-based meta-learning methods have received widespread attention because of their effectiveness in solving few-shot classification problems. However, the scarcity of data frequently results in suboptimal embeddings, causing a discrepancy between anticipated class prototypes and those derived from the support set. These problems severely limit the generalizability of such methods, necessitating further development of Few-Shot Learning (FSL). In this study, we propose the Contrastive Prototype Network (CPN) consisting of three components: (1) Contrastive learning proposed as an auxiliary path to reduce the distance between homogeneous samples and amplify the differences between heterogeneous samples, thereby enhancing the effectiveness and quality of embeddings; (2) A pseudo-prototype strategy proposed to address the bias in prototypes, whereby the pseudo prototypes generated using query set samples are integrated with the initial prototypes to obtain more representative prototypes; (3) A new data augmentation technique, mixupPatch, introduced to alleviate the issue of insufficient data samples, whereby enhanced images are generated by blending the images and labels from different samples, to increase the number of samples. Extensive experiments and ablation studies conducted on five datasets demonstrated that CPN achieves robust results against recent solutions.

Decoupled Cross-Modal Transformer for Referring Video Object Segmentation.

Referring video object segmentation (R-VOS) is a fundamental vision-language task which aims to segment the target referred by language expression in all video frames. Existing query-based R-VOS methods have conducted in-depth exploration of the interaction and alignment between visual and linguistic features but fail to transfer the information of the two modalities to the query vector with balanced intensities. Furthermore, most of the traditional approaches suffer from severe information loss in the process of multi-scale feature fusion, resulting in inaccurate segmentation. In this paper, we propose DCT, an end-to-end decoupled cross-modal transformer for referring video object segmentation, to better utilize multi-modal and multi-scale information. Specifically, we first design a Language-Guided Visual Enhancement Module (LGVE) to transmit discriminative linguistic information to visual features of all levels, performing an initial filtering of irrelevant background regions. Then, we propose a decoupled transformer decoder, using a set of object queries to gather entity-related information from both visual and linguistic features independently, mitigating the attention bias caused by feature size differences. Finally, the Cross-layer Feature Pyramid Network (CFPN) is introduced to preserve more visual details by establishing direct cross-layer communication. Extensive experiments have been carried out on A2D-Sentences, JHMDB-Sentences and Ref-Youtube-VOS. The results show that DCT achieves competitive segmentation accuracy compared with the state-of-the-art methods.