arXiv subjects

Bin Yao

Publications and source records attributed to Bin Yao.

16 recordsLinked to original sources

arXiv2026

Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification

Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain features. Confined to this single perspective, models inevitably suffer from inherent texture biases, entangling essential structural details with high-frequency background noise. Furthermore, lacking cross-view geometric constraints, single-view metrics tend to overfit this noise, resulting in structural instability under few-shot conditions. To address these issues, this paper proposes the Frequency-Enhanced Dual-Subspace Network (FEDSNet). Specifically, FEDSNet utilizes the Discrete Cosine Transform (DCT) and a low-pass filtering mechanism to explicitly isolate low-frequency global structural components from spatial features, thereby suppressing background interference. Truncated Singular Value Decomposition (SVD) is employed to construct independent, low-rank linear subspaces for both spatial texture and frequency structural features. An adaptive gating mechanism is designed to dynamically fuse the projection distances from these dual views. This strategy leverages the structural stability of the frequency subspace to prevent the spatial subspace from overfitting to background features. Extensive experiments on four benchmark datasets - CUB-200-2011, Stanford Cars, Stanford Dogs, and FGVC-Aircraft - demonstrate that FEDSNet exhibits excellent classification performance and robustness, achieving highly competitive results compared to existing metric learning algorithms. Complexity analysis further confirms that the proposed network achieves a favorable balance between high accuracy and computational efficiency, providing an effective new paradigm for few-shot fine-grained visual recognition.

cs.CV↗

arXiv2026

SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)

In open Federated Learning (FL) environments where no central authority exists, ensuring collaboration fairness relies on decentralized reward settlement, yet the prohibitive cost of permissionless blockchains directly clashes with the high-frequency, iterative nature of model training. Existing solutions either compromise decentralization or suffer from scalability bottlenecks due to linear on-chain costs. To address this, we present SettleFL, a trustless and scalable reward settlement protocol designed to minimize total economic friction by offering a family of two interoperable protocols. Leveraging a shared domain-specific circuit architecture, SettleFL offers two interoperable strategies: (1) a Commit-and-Challenge variant that minimizes on-chain costs via optimistic execution and dispute-driven arbitration, and (2) a Commit-with-Proof variant that guarantees instant finality through per-round validity proofs. This design allows the protocol to flexibly adapt to varying latency and cost constraints while enforcing rational robustness without trusted coordination. We conduct extensive experiments combining real FL workloads and controlled simulations. Results show that SettleFL remains practical when scaling to 800 participants, achieving substantially lower gas cost.

cs.CR↗

arXiv2025

LMG Index: A Robust and Efficient Learned Index Framework for Multi-Dimensional Performance Balance

Index structures are fundamental for efficient query processing on large-scale datasets. Learned indexes model the indexing process as a prediction problem to overcome the inherent trade-offs of traditional indexes. However, most existing learned indexes optimize only for limited objectives like query latency or space usage, neglecting other practical evaluation dimensions such as update efficiency and stability. Moreover, many learned indexes rely on assumptions about data distributions or workloads, lacking theoretical guarantees when facing unknown or evolving scenarios, which limits their generality in real-world systems. In this paper, we propose LMG, a robust and efficient learned index framework designed for multi-dimensional performance balance. LMG integrates a decoupled routing structure with theoretical $O(1)$ complexity for fixed key types and an optimal error threshold training algorithm that approaches $O(1)$ overhead in practice. Furthermore, the framework enhances query performance by optimizing gap allocation. Extensive evaluations show that our framework achieves competitive or leading performance across all key evaluation dimensions, including bulk loading (up to 7.55$\times$ faster), point queries (up to 1.68$\times$ faster), range queries (up to 11.41$\times$ faster), and mixed read-write throughput (up to 3.50$\times$ faster). Furthermore, LMG ensures robust long-term stability and high space efficiency (up to 6.26$\times$ smaller footprint). These results demonstrate that LMG significantly mitigates the multi-dimensional performance trade-offs often observed in state-of-the-art approaches, offering a balanced and efficient framework.

cs.DB↗

arXiv2025

EDBench: Large-Scale Electron Density Data for Molecular Modeling

Existing molecular machine learning force fields (MLFFs) generally focus on the learning of atoms, molecules, and simple quantum chemical properties (such as energy and force), but ignore the importance of electron density (ED) $ρ(r)$ in accurately understanding molecular force fields (MFFs). ED describes the probability of finding electrons at specific locations around atoms or molecules, which uniquely determines all ground state properties (such as energy, molecular structure, etc.) of interactive multi-particle systems according to the Hohenberg-Kohn theorem. However, the calculation of ED relies on the time-consuming first-principles density functional theory (DFT) which leads to the lack of large-scale ED data and limits its application in MLFFs. In this paper, we introduce EDBench, a large-scale, high-quality dataset of ED designed to advance learning-based research at the electronic scale. Built upon the PCQM4Mv2, EDBench provides accurate ED data, covering 3.3 million molecules. To comprehensively evaluate the ability of models to understand and utilize electronic information, we design a suite of ED-centric benchmark tasks spanning prediction, retrieval, and generation. Our evaluation on several state-of-the-art methods demonstrates that learning from EDBench is not only feasible but also achieves high accuracy. Moreover, we show that learning-based method can efficiently calculate ED with comparable precision while significantly reducing the computational cost relative to traditional DFT calculations. All data and benchmarks from EDBench will be freely available, laying a robust foundation for ED-driven drug discovery and materials science.

physics.chem-ph↗

arXiv2025

TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning

High-dimensional vector similarity search (HVSS) is critical for many data processing and AI applications. However, traditional HVSS methods often require extensive data access for distance calculations, leading to inefficiencies. Triangle-inequality-based lower bound pruning is a widely used technique to reduce the number of data access in low-dimensional spaces but becomes less effective in high-dimensional settings. This is attributed to the "distance concentration" phenomenon, where the lower bounds derived from the triangle inequality become too small to be useful. To address this, we propose TRIM, which enhances the effectiveness of traditional triangle-inequality-based pruning in high-dimensional vector similarity search using two key ways: (1) optimizing landmark vectors used to form the triangles, and (2) relaxing the lower bounds derived from the triangle inequality, with the relaxation degree adjustable according to user's needs. TRIM is a versatile operation that can be seamlessly integrated into both memory-based (e.g., HNSW, IVFPQ) and disk-based (e.g., DiskANN) HVSS methods, reducing distance calculations and disk access. Extensive experiments show that TRIM enhances memory-based methods, improving graph-based search by up to 90% and quantization-based search by up to 200%, while achieving a pruning ratio of up to 99%. It also reduces I/O costs by up to 58% and improves efficiency by 102% for disk-based methods, while preserving high query accuracy.

cs.DB↗

arXiv2025

PGTuner: An Efficient Framework for Automatic and Transferable Configuration Tuning of Proximity Graphs

Approximate Nearest Neighbor Search (ANNS) plays a crucial role in many key areas. Proximity graphs (PGs) are the leading method for ANNS, offering the best balance between query efficiency and accuracy. However, their performance heavily depends on various construction and query parameters, which are difficult to optimize due to their complex inter-dependencies. Given that users often prioritize specific accuracy levels, efficiently identifying the optimal PG configurations to meet these targets is essential. Although some studies have explored automatic configuration tuning for PGs, they are limited by inefficiencies and suboptimal results. These issues stem from the need to construct numerous PGs for searching and re-tuning from scratch whenever the dataset changes, as well as the failure to capture the complex dependencies between configurations, query performance, and tuning objectives. To address these challenges, we propose PGTuner, an efficient framework for automatic PG configuration tuning leveraging pre-training knowledge and model transfer techniques. PGTuner improves efficiency through a pre-trained query performance prediction (QPP) model, eliminating the need to build multiple PGs. It also features a deep reinforcement learning-based parameter configuration recommendation (PCR) model to recommend optimal configurations for specific datasets and accuracy targets. Additionally, PGTuner incorporates out-of-distribution detection and deep active learning for efficient tuning in dynamic scenarios and transferring to new datasets. Extensive experiments demonstrate that PGTuner can stably achieve the top-level tuning effect across different datasets while significantly improving tuning efficiency by up to 14.69X, with a 14.64X boost in dynamic scenarios. The code and data for PGTuner are available online at https://github.com/hao-duan/PGTuner.

cs.DB↗

arXiv2025

UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search

This paper presents an efficient and scalable framework for Range Filtered Approximate Nearest Neighbors Search (RF-ANNS) over high-dimensional vectors associated with attribute values. Given a query vector $q$ and a range $[l, h]$, RF-ANNS aims to find the approximate $k$ nearest neighbors of $q$ among data whose attribute values fall within $[l, h]$. Existing methods including pre-, post-, and hybrid filtering strategies that perform attribute range filtering before, after, or during the ANNS process, all suffer from significant performance degradation when query ranges shift. Though building dedicated indexes for each strategy and selecting the best one based on the query range can address this problem, it leads to index consistency and maintenance issues. Our framework, called UNIFY, constructs a unified Proximity Graph-based (PG-based) index that seamlessly supports all three strategies. In UNIFY, we introduce SIG, a novel Segmented Inclusive Graph, which segments the dataset by attribute values. It ensures the PG of objects from any segment combinations is a sub-graph of SIG, thereby enabling efficient hybrid filtering by reconstructing and searching a PG from relevant segments. Moreover, we present Hierarchical Segmented Inclusive Graph (HSIG), a variant of SIG which incorporates a hierarchical structure inspired by HNSW to achieve logarithmic hybrid filtering complexity. We also implement pre- and post-filtering for HSIG by fusing skip list connections and compressed HNSW edges into the hierarchical graph. Experimental results show that UNIFY delivers state-of-the-art RF-ANNS performance across small, mid, and large query ranges.

cs.DS↗

arXiv2025

A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving

Vision-Language Models (VLMs) have demonstrated notable promise in autonomous driving by offering the potential for multimodal reasoning through pretraining on extensive image-text pairs. However, adapting these models from broad web-scale data to the safety-critical context of driving presents a significant challenge, commonly referred to as domain shift. Existing simulation-based and dataset-driven evaluation methods, although valuable, often fail to capture the full complexity of real-world scenarios and cannot easily accommodate repeatable closed-loop testing with flexible scenario manipulation. In this paper, we introduce a hierarchical real-world test platform specifically designed to evaluate VLM-integrated autonomous driving systems. Our approach includes a modular, low-latency on-vehicle middleware that allows seamless incorporation of various VLMs, a clearly separated perception-planning-control architecture that can accommodate both VLM-based and conventional modules, and a configurable suite of real-world testing scenarios on a closed track that facilitates controlled yet authentic evaluations. We demonstrate the effectiveness of the proposed platform`s testing and evaluation ability with a case study involving a VLM-enabled autonomous vehicle, highlighting how our test framework supports robust experimentation under diverse conditions.

cs.RO↗

arXiv2024

Enhancing Heterogeneous Knowledge Graph Completion with a Novel GAT-based Approach

Knowledge graphs (KGs) play a vital role in enhancing search results and recommendation systems. With the rapid increase in the size of the KGs, they are becoming inaccuracy and incomplete. This problem can be solved by the knowledge graph completion methods, of which graph attention network (GAT)-based methods stand out since their superior performance. However, existing GAT-based knowledge graph completion methods often suffer from overfitting issues when dealing with heterogeneous knowledge graphs, primarily due to the unbalanced number of samples. Additionally, these methods demonstrate poor performance in predicting the tail (head) entity that shares the same relation and head (tail) entity with others. To solve these problems, we propose GATH, a novel GAT-based method designed for Heterogeneous KGs. GATH incorporates two separate attention network modules that work synergistically to predict the missing entities. We also introduce novel encoding and feature transformation approaches, enabling the robust performance of GATH in scenarios with imbalanced samples. Comprehensive experiments are conducted to evaluate the GATH's performance. Compared with the existing SOTA GAT-based model on Hits@10 and MRR metrics, our model improves performance by 5.2% and 5.2% on the FB15K-237 dataset, and by 4.5% and 14.6% on the WN18RR dataset, respectively.

cs.LG↗

arXiv2024

CS3: Cascade SAM for Sperm Segmentation

Automated sperm morphology analysis plays a crucial role in the assessment of male fertility, yet its efficacy is often compromised by the challenges in accurately segmenting sperm images. Existing segmentation techniques, including the Segment Anything Model(SAM), are notably inadequate in addressing the complex issue of sperm overlap-a frequent occurrence in clinical samples. Our exploratory studies reveal that modifying image characteristics by removing sperm heads and easily segmentable areas, alongside enhancing the visibility of overlapping regions, markedly enhances SAM's efficiency in segmenting intricate sperm structures. Motivated by these findings, we present the Cascade SAM for Sperm Segmentation (CS3), an unsupervised approach specifically designed to tackle the issue of sperm overlap. This method employs a cascade application of SAM to segment sperm heads, simple tails, and complex tails in stages. Subsequently, these segmented masks are meticulously matched and joined to construct complete sperm masks. In collaboration with leading medical institutions, we have compiled a dataset comprising approximately 2,000 unlabeled sperm images to fine-tune our method, and secured expert annotations for an additional 240 images to facilitate comprehensive model assessment. Experimental results demonstrate superior performance of CS3 compared to existing methods.

eess.IV↗

arXiv2022

QDR-Tree: An Efficient Index Scheme for Complex Spatial Keyword Query

With the popularity of mobile devices and the development of geo-positioning technology, location-based services (LBS) attract much attention and top-k spatial keyword queries become increasingly complex. It is common to see that clients issue a query to find a restaurant serving pizza and steak, low in price and noise level particularly. However, most of prior works focused only on the spatial keyword while ignoring these independent numerical attributes. In this paper we demonstrate, for the first time, the Attributes-Aware Spatial Keyword Query (ASKQ), and devise a two-layer hybrid index structure called Quad-cluster Dual-filtering R-Tree (QDR-Tree). In the keyword cluster layer, a Quad-Cluster Tree (QC-Tree) is built based on the hierarchical clustering algorithm using kernel k-means to classify keywords. In the spatial layer, for each leaf node of the QC-Tree, we attach a Dual-Filtering R-Tree (DR-Tree) with two filtering algorithms, namely, keyword bitmap-based and attributes skyline-based filtering. Accordingly, efficient query processing algorithms are proposed. Through theoretical analysis, we have verified the optimization both in processing time and space consumption. Finally, massive experiments with real-data demonstrate the efficiency and effectiveness of QDR-Tree.

cs.DS↗

arXiv2021

A Survey of RDF Stores & SPARQL Engines for Querying Knowledge Graphs

RDF has seen increased adoption in recent years, prompting the standardization of the SPARQL query language for RDF, and the development of local and distributed engines for processing SPARQL queries. This survey paper provides a comprehensive review of techniques and systems for querying RDF knowledge graphs. While other reviews on this topic tend to focus on the distributed setting, the main focus of the work is on providing a comprehensive survey of state-of-the-art storage, indexing and query processing techniques for efficiently evaluating SPARQL queries in a local setting (on one machine). To keep the survey self-contained, we also provide a short discussion on graph partitioning techniques used in the distributed setting. We conclude by discussing contemporary research challenges for further improving SPARQL query engines. This extended version also provides a survey of over one hundred SPARQL query engines and the techniques they use, along with twelve benchmarks and their features.

cs.DB↗

arXiv2021

Global-Position Tracking Control of 3-D Bipedal Walking via Virtual Constraint Design and Multiple Lyapunov Analysis

A safety-critical measure of legged locomotion performance is a robot's ability to track its desired time-varying position trajectory in an environment, which is herein termed as "global-position tracking". This paper introduces a nonlinear control approach that achieves asymptotic global-position tracking for three-dimensional (3-D) bipedal robot walking. Designing a global-position tracking controller presents a challenging problem due to the complex hybrid robot model and the time-varying desired global-position trajectory. Towards tackling this problem, the first main contribution is the construction of impact invariance to ensure all desired trajectories respect the foot-landing impact dynamics, which is a necessary condition for realizing asymptotic tracking of hybrid walking systems. Thanks to their independence of the desired global position, these conditions can be exploited to decouple the higher-level planning of the global position and the lower-level planning of the remaining trajectories, thereby greatly alleviating the computational burden of motion planning. The second main contribution is the Lyapunov-based stability analysis of the hybrid closed-loop system, which produces sufficient conditions to guide the controller design for achieving asymptotic global-position tracking during fully actuated walking. Simulations and experiments on a 3-D bipedal robot with twenty revolute joints confirm the validity of the proposed control approach in guaranteeing accurate tracking.

cs.RO↗

arXiv2020

Storage, Indexing, Query Processing, and Benchmarking in Centralized and Distributed RDF Engines: A Survey

The recent advancements of the Semantic Web and Linked Data have changed the working of the traditional web. There is significant adoption of the Resource Description Framework (RDF) format for saving of web-based data. This massive adoption has paved the way for the development of various centralized and distributed RDF processing engines. These engines employ various mechanisms to implement critical components of the query processing engines such as data storage, indexing, language support, and query execution. All these components govern how queries are executed and can have a substantial effect on the query runtime. For example, the storage of RDF data in various ways significantly affects the data storage space required and the query runtime performance. The type of indexing approach used in RDF engines is critical for fast data lookup. The type of the underlying querying language (e.g., SPARQL or SQL) used for query execution is a crucial optimization component of the RDF storage solutions. Finally, query execution involving different join orders significantly affects the query response time. This paper provides a comprehensive review of centralized and distributed RDF engines in terms of storage, indexing, language support, and query execution.

cs.DB↗

arXiv2020

Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration

The research interest in specialized hardware accelerators for deep neural networks (DNN) spikes recently owing to their superior performance and efficiency. However, today's DNN accelerators primarily focus on accelerating specific "kernels" such as convolution and matrix multiplication, which are vital but only part of an end-to-end DNN-enabled application. Meaningful speedups over the entire application often require supporting computations that are, while massively parallel, ill-suited to DNN accelerators. Integrating a general-purpose processor such as a CPU or a GPU incurs significant data movement overhead and leads to resource under-utilization on the DNN accelerators. We propose Simultaneous Multi-mode Architecture (SMA), a novel architecture design and execution model that offers general-purpose programmability on DNN accelerators in order to accelerate end-to-end applications. The key to SMA is the temporal integration of the systolic execution model with the GPU-like SIMD execution model. The SMA exploits the common components shared between the systolic-array accelerator and the GPU, and provides lightweight reconfiguration capability to switch between the two modes in-situ. The SMA achieves up to 63% performance improvement while consuming 23% less energy than the baseline Volta architecture with TensorCore.

cs.DC↗

arXiv2019

A Hybrid Data Cleaning Framework using Markov Logic Networks

With the increase of dirty data, data cleaning turns into a crux of data analysis. Most of the existing algorithms rely on either qualitative techniques (e.g., data rules) or quantitative ones (e.g., statistical methods). In this paper, we present a novel hybrid data cleaning framework on top of Markov logic networks (MLNs), termed as MLNClean, which is capable of cleaning both schema-level and instance-level errors. MLNClean mainly consists of two cleaning stages, namely, first cleaning multiple data versions separately (each of which corresponds to one data rule), and then deriving the final clean data based on multiple data versions. Moreover, we propose a series of techniques/concepts, e.g., the MLN index, the concepts of reliability score and fusion score, to facilitate the cleaning process. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of MLNClean to the state-of-the-art approach in terms of both accuracy and efficiency.

cs.DB↗