Set Of Queries Research Articles

Exploiting the Sparseness of Control-Flow and Call Graphs for Efficient and On-Demand Algebraic Program Analysis

Algebraic Program Analysis (APA) is a ubiquitous framework that has been employed as a unifying model for various problems in data-flow analysis, termination analysis, invariant generation, predicate abstraction and a wide variety of other standard static analysis tasks. APA models program summaries as elements of a regular algebra . Suppose that a summary in A is assigned to every transition of the program and that we aim to compute the effect of running the program starting at line s and ending at line t . APA first computes a regular expression capturing all program paths of interest. In case of intraprocedural analysis, models all paths from s to t , whereas in the interprocedural case it models all interprocedurally-valid paths, i.e. ‍paths that go back to the right caller function when a callee returns. This regular expression is then interpreted over the algebra to obtain the desired result. Suppose the program has n lines of code and each evaluation of an operation in the regular algebra takes O ( k ) time. It is well-known that a single APA query, or a set of queries with the same starting point s , can be answered in O ( n · α( n ) · k ), where α is the inverse Ackermann function. In this work, we consider an on-demand setting for APA: the program is given in the input and can be preprocessed. The analysis has to then answer a large number of on-line queries, each providing a pair ( s , t ) of program lines which are the start and end point of the query, respectively. The goal is to avoid the significant cost of running a fresh APA instance for each query. Our main contribution is a series of algorithms that, after a lightweight preprocessing of O ( n · lg n · k ), answer each query in O ( k ) time. In other words, our preprocessing has almost the same asymptotic complexity as a single APA query, except for a sub-logarithmic factor, and then every future query is answered instantly, i.e. ‍by a constant number of operations in the algebra. We achieve this remarkable speedup by relying on certain structural sparsity properties of control-flow and call graphs (CFGs and CGs). Specifically, we exploit the fact that control-flow graphs of real-world programs have a tree-like structure and bounded treewidth and nesting depth and that their call graphs have small treedepth in comparison to the size of the program. Finally, we provide experimental results demonstrating the effectiveness and efficiency of our approach and showing that it beats the runtime of classical APA by several orders of magnitude.

A Shifting Filter Framework for Dynamic Set Queries

Set query is a fundamental problem in computer systems. Plenty of applications rely on the query results of membership, association, and multiplicity. A traditional method that addresses such a fundamental problem is derived from Bloom filter. However, such methods may fail to support element deletion, require additional filters or apriori knowledge, making them unamenable to a high-performance implementation for dynamic set representation and query. In this paper, we envision a novel sketch framework that is multi-functional, non-parametric, space efficient, and deletable. As far as we know, none of the existing designs can guarantee such features simultaneously. To this end, we present a general shifting framework to represent auxiliary information (such as multiplicity, association) with the offset. Thereafter, we specify such design philosophy for a hash table horizontally at the slot level, as well as vertically at the bucket level. Theoretical and experimental results jointly demonstrate that our design works exceptionally well with three types of set queries under small memory.

Few-Shot Person Re-Identification Based on Meta-Learning with a Compression and Stimulation Module

This paper proposes a few-shot pedestrian re-identification (Re-ID) model based on an improved ResNet50 with a compression and stimulation module, which is named CS-ResNet50. It combines the meta-learning framework with metric learning. This method first compresses residual network channels, then stimulates them to achieve the effect of feature weighting, ultimately making feature extraction more accurate. The research makes the model learn how to finish new tasks efficiently from its experience that it has obtained in the training process of former subtasks. In each subtask, the dataset is divided into a gallery set and a query set, where the model parameters are trained. In this way, the model can be trained efficiently and adopted to new tasks rapidly, which could solve few-shot Re-ID problems. Compared with the baseline, the proposed model improves two indicators efficiently on two Re-ID datasets and achieves better Re-ID effect in few-shot mode.

MM-GANN-DDI: Multimodal Graph-Agnostic Neural Networks for Predicting Drug–Drug Interaction Events

Personalized treatment of complex diseases relies on combined medication. However, the occurrence of unexpected drug–drug interactions (DDIs) in these combinations can lead to adverse effects or even fatalities. Although recent computational methods exhibit promising performance in DDI screening, their practical implementation faces two significant challenges: (i) the availability of comprehensive datasets to support clinical application, and (ii) the ability to infer DDI types for new drugs beyond the existing dataset coverage. To mitigate these challenges, we propose MM-GANN-DDI: a Multimodal Graph-Agnostic Neural Network for Predicting Drug–Drug Interaction Events. We first mine six drug modalities and incorporate a graph attention (GAT) mechanism to fuse these modalities with the topological features of the DDI graph. We further propose a novel graph neural network training mechanism called graph-agnostic meta-training (GAMT), which effectively leverages topological information from the DDI graph and efficiently predicts DDI types for new drugs beyond the available dataset. Specifically, GAMT samples meta-graphs from the original DDI graph, splitting them into support and query sets to simulate seen and unseen drugs. Two-level optimizations are applied to enhance the model’s generalization capability.We evaluate our model on two datasets (DB-v1 and DB-v2) across three tasks. Our MM-GANN-DDI demonstrates competitive performance on all three tasks. Notably, in Task 2, which focuses on predicting DDI types for drugs outside the dataset, our proposed model outperforms other methods, exhibiting an improvement of 4.6 percentage points in AUPR on DB-v1 and 5.9 percentage points on DB-v2. Additionally, our model surpasses state-of-the-art methods and classic approaches in terms of accuracy, F1 score, precision, and recall. Ablation experiments provide further validation of the effectiveness of the proposed model design. Importantly, our model exhibits the potential to discover unobserved DDIs, demonstrating its practical application in clinical medication.

Scientific Article Writing: Will ChatGPT Help?

The emergence of artificial intelligence language services has raised hopes related to facilitating the task of publication activity. Members of the academic community wondered whether chatbots could optimize the process of scientific writing. ChatGPT, a language model capable of, among other things, generating scholarly texts, received particular attention. The cases of writing academic papers using ChatGPT have led to a number of publications analyzing the pros and cons of using this neural network. In this paper, we investigate the possibility of using ChatGPT to write an introduction to a scientific paper on a topical issue of the Arctic governance. A set of queries to ChatGPT network, based on the logic of the commonly accepted in academia publication format IMRAD, has being developed. This format is characterized by structural and functional elements, which served as a logical basis for the queries. The responses received from ChatGPT were analyzed for their compliance with the requirements for a scientific article, according to the IMRAD publication format. The result of the analysis showed that ChatGPT is not able to meet the requirements for publishing a scientific article in the modern scientific publication discourse.

Collaborative Self-Supervised Transductive Few-Shot Learning for Remote Sensing Scene Classification

With the advent of deep learning and the accessibility of massive data, scene classification algorithms based on deep learning have been extensively researched and have achieved exciting developments. However, the success of deep models often relies on a large amount of annotated remote sensing data. Additionally, deep models are typically trained and tested on the same set of classes, leading to compromised generalization performance when encountering new classes. This is where few-shot learning aims to enable models to quickly generalize to new classes with only a few reference samples. In this paper, we propose a novel collaborative self-supervised transductive few-shot learning (CS2TFSL) algorithm for remote sensing scene classification. In our approach, we construct two distinct self-supervised auxiliary tasks to jointly train the feature extractor, aiming to obtain a powerful representation. Subsequently, the feature extractor’s parameters are frozen, requiring no further training, and transferred to the inference stage. During testing, we employ transductive inference to enhance the associative information between the support and query sets by leveraging additional sample information in the data. Extensive comparisons with state-of-the-art few-shot scene classification algorithms on the WHU-RS19 and NWPU-RESISC45 datasets demonstrate the effectiveness of the proposed CS2TFSL. More specifically, CS2TFSL ranks first in the settings of five-way one-shot and five-way five-shot. Additionally, detailed ablation experiments are conducted to analyze the CS2TFSL. The experimental results reveal significant and promising performance improvements in few-shot scene classification through the combination of self-supervised learning and direct transductive inference.

Hierarchical Knowledge Propagation and Distillation for Few-Shot Learning

Recent research efforts on Few-Shot Learning (FSL) have achieved extensive progress. However, the existing efforts primarily focus on the transductive setting of FSL, which is heavily challenged by the limited quantity of the unlabeled query set. Although a few inductive-based FSL methods have been studied, most of them emphasize learning superb feature extraction networks. As a result, they may ignore the relations between sample-level and class-level representations, which are particularly crucial when labeled samples are scarce. This paper proposes an inductive FSL framework that leverages the Hierarchical Knowledge Propagation and Distillation, named HKPD. To learn more discriminative sample-level representations, HKPD first constructs a sample-level information propagation module that explores pairwise sample relations. Subsequently, a class-level information propagation module is designed to obtain and update the class-level information. Moreover, a self-distillation module is adopted to further improve the learned representations by propagating the obtained knowledge across this hierarchical architecture. Extensive experiments conducted on the commonly used few-shot benchmark datasets demonstrate the superiority of the proposed HKPD method, which outperforms the current state-of-the-art methods.

LORA, Lipid Over-Representation Analysis Based on Structural Information.

With the increasing number of lipidomic studies, there is a need for an efficient and automated analysis of lipidomic data. One of the challenges faced by most existing approaches to lipidomic data analysis is lipid nomenclature. The systematic nomenclature of lipids contains all available information about the molecule, including its hierarchical representation, which can be used for statistical evaluation. The Lipid Over-Representation Analysis (LORA) web application (https://lora.metabolomics.fgu.cas.cz) analyzes this information using the Java-based Goslin framework, which translates lipid names into a standardized nomenclature. Goslin provides the level of lipid hierarchy, including information on headgroups, acyl chains, and their modifications, up to the "complete structure" level. LORA allows the user to upload the experimental query and reference data sets, select a grammar for lipid name normalization, and then process the data. The user can then interactively explore the results and perform lipid over-representation analysis based on selected criteria. The results are graphically visualized according to the lipidome hierarchy. The lipids present in the most over-represented terms (lipids with the highest number of enriched shared structural features) are defined as Very Important Lipids (VILs). For example, the main result of a demo data set is the information that the query is significantly enriched with "glycerophospholipids" containing "acyl 20:4" at the "sn-2 position". These terms define a set of VILs (e.g., PC 18:2/20:4;O and PE 16:0/20:4(5,8,10,14);OH). All results, graphs, and visualizations are summarized in a report. LORA is a tool focused on the smart mining of epilipidomics data sets to facilitate their interpretation at the molecular level.

Few-shot Named Entity Recognition with Joint Token and Sentence Awareness

ABSTRACT Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Recently, few-shot models have been used for Named Entity Recognition (NER). Prototypical network shows high efficiency on few-shot NER. However, existing prototypical methods only consider the similarity of tokens in query sets and support sets and ignore the semantic similarity among the sentences which contain these entities. We present a novel model, Few-shot Named Entity Recognition with Joint Token and Sentence Awareness (JTSA), to address the issue. The sentence awareness is introduced to probe the semantic similarity among the sentences. The Token awareness is used to explore the similarity of the tokens. To further improve the robustness and results of the model, we adopt the joint learning scheme on the few-shot NER. Experimental results demonstrate that our model outperforms state-of-the-art models on two standard Few-shot NER datasets.

MARN: Multi-level Attentional Reconstruction Networks for Weakly Supervised Video Temporal Grounding

Video temporal grounding is a challenging task in computer vision that involves localizing a video segment semantically related to a given query from a set of videos and queries. In this paper, we propose a novel weakly-supervised model called the Multi-level Attentional Reconstruction Networks (MARN), which is trained on video-sentence pairs. During the training phase, we leverage the idea of attentional reconstruction to train an attention map that can reconstruct the given query. At inference time, proposals are ranked based on attention scores to localize the most suitable segment. In contrast to previous methods, MARN effectively aligns video-level supervision and proposal scoring, thereby reducing the training-inference discrepancy. In addition, we incorporate a multi-level framework that encompasses both proposal-level and clip-level processes. The proposal-level process generates and scores variable-length time sequences, while the clip-level process generates and scores fix-length time sequences to refine the predicted scores of the proposal in both training and testing. To improve the feature representation of the video, we propose a novel representation mechanism that utilizes intra-proposal information and adopts 2D convolution to extract inter-proposal clues for learning reliable attention maps. By accurately representing these proposals, we can better align them with the textual modalities, and thus facilitate the learning of the model. Our proposed MARN is evaluated on two benchmark datasets, and extensive experiments demonstrate its superiority over existing methods.

Are NoSQL Databases Affected by Schema?

During data modelling, NoSQL databases are usually considered schema-less databases. They do not support rigid schema as traditional databases. Instead, offer flexibility and support dynamic schema, which means schema design can be changed at run time to support analytical tasks. NoSQL databases allow storing similar information with multiple schemas, which facilitates data evolution by eliminating restrictions on the schema. It raises the question of whether the schema matters in NoSQL databases, given that explicit schema declaration is not required before data storage. Furthermore, if the schema does matter, what is its potential impact on application performance? This paper examines these questions by taking three types of NoSQL databases: Document store, Column store, and Key-Value store. All possible schema structure alternatives are designed using a sample Entity Relationship (ER) model. Then, a set of common queries are performed on various schema alternatives to analyse the impact of query performance in terms of query response time, speedup factor, read and write Latency, and database size. The results suggest that the scheme alternatives affect the database performance in different NoSQL models.

FREDA: Few-Shot Relation Extraction Based on Data Augmentation

The primary task of few-shot relation extraction is to quickly learn the features of relation classes from a few labelled instances and predict the semantic relations between entity pairs in new instances. Most existing few-shot relation extraction methods do not fully utilize the relation information features in sentences, resulting in difficulties in improving the performance of relation classification. Some researchers have attempted to incorporate external information, but the results have been unsatisfactory when applied to different domains. In this paper, we propose a method that utilizes triple information for data augmentation, which can alleviate the issue of insufficient instances and possesses strong domain adaptation capabilities. Firstly, we extract relation and entity pairs from the instances in the support set, forming relation triple information. Next, the sentence information and relation triple information are encoded using the same sentence encoder. Then, we construct an interactive attention module to enable the query set instances to interact separately with the support set instances and relation triple instances. The module pays greater attention to highly interactive parts between instances and assigns them higher weights. Finally, we merge the interacted support set representation and relation triple representation. To our knowledge, we are the first to propose a method that utilizes triple information for data augmentation in relation extraction. In our experiments on the standard datasets FewRel1.0 and FewRel2.0 (domain adaptation), we observed substantial improvements without including external information.

Can we improve meta-learning model in few-shot learning by aligning data distributions?

Meta-learning becomes a promising way to solve the few-shot learning problem in recent research. This paradigm mainly relies on hierarchical architecture and episodic training to achieve good generalization on the new learning task. However, as we know, support and query sets in each training task in episodic training only contain a few data points. Too limited training data can lead to data discrepancy between the training and test data which further hurts the performance of learning models in classical supervised and semi-supervised learning. Hence, there is an interesting question: Can we also improve the meta-learning model in few-shot learning by aligning the data distributions of support and query sets? In this work, we try to answer this question. Firstly, we give a theoretical analysis of the generalization ability of meta-learning to show that eliminating the data-distribution discrepancy between the support and query sets in each training task can improve the meta-learning model in few-shot learning. Next, we design an experiment to further verify our analysis. The experimental results show that aligning the data distributions is crucial and even can help the learning model trained by the classical batch-based training achieve better performance on unseen few-shot learning tasks. Furthermore, we also propose two simple meta-batch normalization methods following our result which can be integrated into recent meta-learning methods to improve their performance in few-shot learning.

Few-Shot Object Detection in Remote Sensing Imagery via Fuse Context Dependencies and Global Features

The rapid development of Earth observation technology has promoted the continuous accumulation of images in the field of remote sensing. However, a large number of remote sensing images still lack manual annotations of objects, which makes the strongly supervised deep learning object detection method not widely used, as it lacks generalization ability for unseen object categories. Considering the above problems, this study proposes a few-shot remote sensing image object detection method that integrates context dependencies and global features. The method can be used to fine-tune the model with a small number of sample annotations based on the model trained in the base class, as a way to enhance the detection capability of new object classes. The method proposed in this study consists of three main modules, namely, the meta-feature extractor (ME), reweighting module (RM), and feature fusion module (FFM). These three modules are respectively used to enhance the context dependencies of the query set features, improve the global features of the support set that contains annotations, and finally fuse the query set features and support set features. The baseline of the meta-feature extractor of the entire framework is based on the optimized YOLOv5 framework. The reweighting module of the support set feature extraction is based on a simple convolutional neural network (CNN) framework, and the foreground feature enhancement of the support sets was made in the preprocessing stage. This study achieved beneficial results in the two benchmark datasets NWPU VHR-10 and DIOR. Compared with the comparison methods, the proposed method achieved the best performance in the object detection of the base class and the novel class.

Interaction Information Guided Prototype Representation Rectification for Few-Shot Relation Extraction

Few-shot relation extraction aims to identify and extract semantic relations between entity pairs using only a small number of annotated instances. Many recently proposed prototype-based methods have shown excellent performance. However, existing prototype-based methods ignore the hidden inter-instance interaction information between the support and query sets, leading to unreliable prototypes. In addition, the current optimization of the prototypical network only relies on cross-entropy loss. It is only concerned with the accuracy of the predicted probability for the correct label, ignoring the differences of other non-correct labels, which cannot account for relation discretization in semantic space. This paper proposes an attentional network of interaction information to obtain a more reliable relation prototype. Firstly, an inter-instance interaction information attention module is designed to mitigate prototype unreliability through interaction information between the support set and query set instances, utilizing category information hidden in the query set. Secondly, the similarity scalar, which is defined by the mixed features of the prototype and the relation and is added to the focal loss to improve the attention of hard examples. We conducted extensive experiments on two standard datasets and demonstrated the validity of our proposed model.

Voxel Benchmarks for 3D Pathfinding: Sandstone, Descent, and Industrial Plants

Voxel grids are an increasingly common enabler for pathfinding in 3D spaces. Currently in this area there exists only a limited number of publicly available benchmarks. This makes it difficult to establish state-of-the-art performance and to compare the strengths and weaknesses of competing search techniques. In this work, we introduce three new and diverse sets of voxel benchmarks intended to help fill this gap. We further describe our methodology for generating and selecting a representative set of pathfinding queries. Our dataset comprises 46 distinct voxel maps and 92,000 problem instances. The data is drawn from distinct application domains: computer video games, industrial plant layouts and sandstone porosity scans. Featuring distinctive geometric properties and a variety of challenging query types, these new datasets allow practitioners to evaluate algorithmic performance across a variety of settings encountered when pathfinding in practice.

An Intermediate Language for General Sparse Format Customization

The inevitable trend of hardware specialization drives an increasing use of custom data formats in processing sparse workloads, which are typically memory-bound. These formats facilitate the automated generation of target-aware data layouts to improve memory access latency and bandwidth utilization. However, existing sparse tensor programming models and compilers offer little or no support for productively customizing the sparse formats. Moreover, since these frameworks adopt an attribute-based approach for format abstraction, they cannot easily be extended to support general format customization. To overcome this deficiency, we propose UniSparse, an intermediate language that provides a unified abstraction for representing and customizing sparse formats. More concretely, we express a sparse format as a map from dense coordinates to a layout tree using a small set of well-defined query and mutation primitives. We also develop a compiler leveraging the MLIR infrastructure, which supports adaptive customization of formats, and automatic code generation of format conversion and compute operations for heterogeneous architectures. We demonstrate the efficacy of our approach through experiments running commonly-used sparse linear algebra operations with hybrid formats on multiple different hardware targets, including an Intel CPU, an NVIDIA GPU, and a simulated processing-in-memory (PIM) device.

Fast Search-by-Classification for Large-Scale Databases Using Index-Aware Decision Trees and Random Forests

The vast amounts of data collected in various domains pose great challenges to modern data exploration and analysis. To find "interesting" objects in large databases, users typically define a query using positive and negative example objects and train a classification model to identify the objects of interest in the entire data catalog. However, this approach requires a scan of all the data to apply the classification model to each instance in the data catalog, making this method prohibitively expensive to be employed in large-scale databases serving many users and queries interactively. In this work, we propose a novel framework for such search-by-classification scenarios that allows users to interactively search for target objects by specifying queries through a small set of positive and negative examples. Unlike previous approaches, our framework can rapidly answer such queries at low cost without scanning the entire database. Our framework is based on an index-aware construction scheme for decision trees and random forests that transforms the inference phase of these classification models into a set of range queries, which in turn can be efficiently executed by leveraging multidimensional indexing structures. Our experiments show that queries over large data catalogs with hundreds of millions of objects can be processed in a few seconds using a single server, compared to hours needed by classical scanning-based approaches.

SEML: Self-Supervised Information-Enhanced Meta-learning for Few-Shot Text Classification

Training a deep-learning text classification model usually requires a large amount of labeled data, yet labeling data are usually labor-intensive and time-consuming. Few-shot text classification focuses on predicting unknown samples using only a few labeled samples. Recently, metric-based meta-learning methods have achieved promising results in few-shot text classification. They use episodic training in labeled samples to enhance the model’s generalization ability. However, existing models only focus on learning from a few labeled samples but neglect to learn from a large number of unlabeled samples. In this paper, we exploit the knowledge learned by the model in unlabeled samples to improve the generalization performance of the meta-network. Specifically, we introduce a novel knowledge distillation method that expands and enriches the meta-learning representation with self-supervised information. Meanwhile, we design a graph aggregation method that efficiently interacts the query set information with the support set information in each task and outputs a more discriminative representation. We conducted experiments on three public few-shot text classification datasets. The experimental results show that our model performs better than the state-of-the-art models in 5-way 1-shot and 5-way 5-shot cases.

SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning

Recent Few-Shot Learning (FSL) methods put emphasis on generating a discriminative embedding features to precisely measure the similarity between support and query sets. Current CNN-based cross-attention approaches generate discriminative representations via enhancing the mutually semantic similar regions of support and query pairs. However, it suffers from two problems: CNN structure produces inaccurate attention map based on local features, and mutually similar backgrounds cause distraction. To alleviate these problems, we design a novel SpatialFormer structure to generate more accurate attention regions based on global features. Different from the traditional Transformer modeling intrinsic instance-level similarity which causes accuracy degradation in FSL, our SpatialFormer explores the semantic-level similarity between pair inputs to boost the performance. Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction. Particularly, SFSA highlights the regions with same semantic information between pair features, and SFTA finds potential foreground object regions of novel feature that are similar to base categories. Extensive experiments show that our methods are effective and achieve new state-of-the-art results on few-shot classification benchmarks.