arXiv subjects

Mingsong Chen

Publications and source records attributed to Mingsong Chen.

At least 19 recordsLinked to original sources

arXiv2026

Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding

Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense captioning methods face significant limitations in processing sparse point cloud data. % Existing approaches that apply Euclidean embedding spaces struggle to simultaneously preserve fine-grained local geometric details and model exponentially growing global semantic hierarchies, leading to either inaccurate localization or disjointed, shallow scene descriptions. % In this work, we propose a novel \textbf{\textsc{Curvature-Aware Captioning}} framework, integrating novel non-Euclidean geodesic attention mechanisms, to resolve the localization-contextualization conflict. % Specifically, self-attention within Oblique space enforces dimensional homogeneity while establishing long-range dependencies. Bidirectional geodesic cross-attention within Lorentz space models hierarchical semantic relationships across scene instances, enabling simultaneous precision in object localization and coherence in scene descriptions. % Theoretical analysis confirms that the curvature complementarity between the Oblique manifold and Lorentz hyperboloid resolves the Euclidean-hyperbolic conflict, ensuring feature stability via isotropic optimization while preserving inherent hierarchical relationships. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate state-of-the-art performance, with significant gains in both localization accuracy and descriptive richness.

cs.CV↗

arXiv2026

HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\times$ and 16$\times$, respectively, compared to the state-of-the-art open-source baseline.

cs.AI↗

arXiv2026

S$^3$GND: An Effective Learning-Based Approach for Subgraph Similarity Search Under Generalized Neighbor Difference Semantics (Technical Report)

Subgraph similarity search over large-scale graphs is a fundamental task that retrieves subgraphs similar to a given query graph from a data graph, and it plays a crucial role in real applications such as protein discovery, social network analysis, and recommendation systems. While prior works on subgraph similarity search studied various graph similarity metrics, in this paper, we propose a novel graph similarity semantics, \textit{generalized neighbor difference} (GND), that accounts for both the keyword-set relationships between vertices and edge-weight differences. We formulate the problem of \textit{subgraph similarity search under the generalized neighbor difference semantics} (S$^3$GND), which retrieves those subgraphs similar to a query graph $q$ under GND semantics. To efficiently tackle the S$^3$GND problem, we propose an effective learning-based approach, which constructs a keyword hypergraph from the data graph, and trains a \textit{hypergraph neural network} (HGNN) model to obtain high-quality keyword embedding representations. We design effective pruning strategies, \textit{keyword embedding MBR}, \textit{vertex-Level ND lower bound}, and \textit{graph-level GND lower bound pruning}, to rule out false alarms of candidate vertices/subgraphs, and devise a tree-based indexing mechanism to facilitate efficient S$^3$GND query answering. We develop an efficient S$^3$GND query-processing algorithm that traverses the index, applies pruning strategies, and returns actual S$^3$GND answers. Finally, we conduct extensive experiments to verify the effectiveness and efficiency of our proposed S$^3$GND approach over both real and synthetic graphs.

cs.DB↗

arXiv2025

Efficient Exact Subgraph Matching via GNN-based Path Dominance Embedding (Technical Report)

The classic problem of exact subgraph matching returns those subgraphs in a large-scale data graph that are isomorphic to a given query graph, which has gained increasing importance in many real-world applications. In this paper, we propose a novel and effective graph neural network (GNN)-based path embedding framework (GNN-PE), which allows efficient exact subgraph matching without introducing false dismissals. Unlike traditional GNN-based graph embeddings that only produce approximate subgraph matching results, in this paper, we carefully devise GNN-based embeddings for paths, such that: if two paths (and 1-hop neighbors of vertices on them) have the subgraph relationship, their corresponding GNN-based embedding vectors will strictly follow the dominance relationship. With such a newly designed property of path dominance embeddings, we are able to propose effective pruning strategies based on path label/dominance embeddings and guarantee no false dismissals for subgraph matching. We build multidimensional indexes over path embedding vectors, and develop an efficient subgraph matching algorithm by traversing indexes over graph partitions in parallel and applying our pruning methods. We also propose a cost-model-based query plan that obtains query paths from the query graph with low query cost. To further optimize our GNN-PE approach, we also propose a more efficient GNN-based path group embedding (GNN-PGE) technique, which performs subgraph matching over grouped path embedding vectors. We design effective pruning strategies (w.r.t. grouped path embeddings) that can significantly reduce the search space during the index traversal. Through extensive experiments, we confirm the efficiency and effectiveness of our proposed GNN-PE and GNN-PGE approaches for exact subgraph matching on both real and synthetic graph data.

cs.DB↗

arXiv2025

OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution

Denoising Diffusion Probabilistic Models (DDPMs) show promising potential in one-step Real-World Image Super-Resolution (Real-ISR). Current one-step Real-ISR methods typically inject the low-quality (LQ) image latent representation at the start or end timestep of the DDPM scheduler. Recent studies have begun to note that the LQ image latent and the pre-trained noisy latent representations are intuitively closer at a mid-timestep. However, a quantitative analysis of these latent representations remains lacking. Considering these latent representations can be decomposed into signal and noise, we propose a method based on the Signal-to-Noise Ratio (SNR) to pre-compute an average optimal mid-timestep for injection. To better approximate the pre-trained noisy latent representation, we further introduce the Latent Representation Refinement (LRR) loss via a LoRA-enhanced VAE encoder. We also fine-tune the backbone of the DDPM-based generative model using LoRA to perform one-step denoising at the average optimal mid-timestep. Based on these components, we present OMGSR, a GAN-based Real-ISR framework that employs a DDPM-based generative model as the generator and a DINOv3-ConvNeXt model with multi-level discriminator heads as the discriminator. We also propose the DINOv3-ConvNeXt DISTS (Dv3CD) loss, which is enhanced for structural perception at varying resolutions. Within the OMGSR framework, we develop OMGSR-S based on SD2.1-base. An ablation study confirms that our pre-computation strategy and LRR loss significantly improve the baseline. Comparative studies demonstrate that OMGSR-S achieves state-of-the-art performance across multiple metrics. Code is available at \hyperlink{Github}{https://github.com/wuer5/OMGSR}.

cs.CV↗

arXiv2025

PDDFormer: Pairwise Distance Distribution Graph Transformer for Crystal Material Property Prediction

Crystal structures can be simplified as a periodic point set that repeats across three-dimensional space along an underlying lattice. Traditionally, crystal representation methods characterize the structure using descriptors such as lattice parameters, symmetry, and space groups. However, in reality, atoms in materials always vibrate above absolute zero, causing their positions to fluctuate continuously. This dynamic behavior disrupts the fundamental periodicity of the lattice, making crystal graphs based on static lattice parameters and conventional descriptors discontinuous under slight perturbations. Chemists proposed the pairwise distance distribution (PDD) method to address this problem. However, the completeness of PDD requires defining a large number of neighboring atoms, leading to high computational costs. Additionally, PDD does not account for atomic information, making it challenging to apply it directly to crystal material property prediction tasks. To tackle these challenges, we introduce the atom-Weighted Pairwise Distance Distribution (WPDD) and Unit cell Pairwise Distance Distribution (UPDD) and apply them to the construction of multi-edge crystal graphs. We demonstrate the continuity and general completeness of crystal graphs under slight atomic position perturbations. Moreover, by modeling PDD as global information and integrating it into matrix-based message passing, we significantly reduce computational costs. Comprehensive evaluation results show that WPDDFormer achieves state-of-the-art predictive accuracy across tasks on benchmark datasets such as the Materials Project and JARVIS-DFT.

cond-mat.mtrl-sci↗

arXiv2025

Efficient Community Detection Over Streaming Bipartite Networks (Technical Report)

The streaming bipartite graph is widely used to model the dynamic relationship between two types of entities in various real-world applications, including movie recommendations, location-based services, and online shopping. Since it contains abundant information, discovering the dense subgraph with high structural cohesiveness (i.e., community detection) in the bipartite streaming graph is becoming a valuable problem. Inspired by this, in this paper, we study the structure of the community on the butterfly motif in the bipartite graph. We propose a novel problem, named Community Detection over Streaming Bipartite Network (CD-SBN), which aims to retrieve qualified communities with user-specific query keywords and high structural cohesiveness at snapshot and continuous scenarios. In particular, we formulate the user relationship score in the weighted bipartite network via the butterfly pattern and define a novel $(k,r,σ)$-bitruss as the community structure. To efficiently tackle the CD-SBN problem, we design effective pruning strategies to rule out false alarms of $(k,r,σ)$-bitruss and propose a hierarchical synopsis to facilitate the CD-SBN processing. We develop efficient algorithms to answer snapshot and continuous CD-SBN queries by traversing the synopsis and applying pruning strategies. With extensive experiments, we demonstrate the performance of our CD-SBN approach on real/synthetic streaming bipartite networks.

cs.SI↗

arXiv2025

Continuous Subgraph Matching via Cost-Model-based Dynamic Vertex Dominance Embeddings (Technical Report)

In many real-world applications such as social network analysis, knowledge graph discovery, biological network analytics, and so on, graph data management has become increasingly important and has drawn much attention from the database community. While many graphs (e.g., Twitter, Wikipedia, etc.) are usually evolving over time, it is of great importance to study the \textit{continuous subgraph matching} (CSM) problem, a fundamental, yet challenging, graph operator, which continuously monitors subgraph matching results over dynamic graphs with a stream of edge updates. To efficiently tackle the CSM problem, we carefully design a general CSM processing framework, based on novel \textit{\underline{D}ynam\underline{I}c \underline{V}ertex Dom\underline{IN}ance \underline{E}mbedding} (DIVINE), which maps vertex neighborhoods into an embedding space to enable efficient subgraph matching and incremental maintenance under dynamic updates. Inspired by low pruning power for high-degree vertices, we propose a new \textit{degree grouping} technique to decompose high-degree star patterns into groups of lower-degree star substructures, and devise \textit{degree-aware star substructure synopses} (DAS$^3$) over embeddings of star substructure groups. We develop efficient algorithms to incrementally maintain dynamic graphs and answer CSM queries by traversing DAS$^3$ synopses and applying our designed \textit{vertex dominance} and \textit{range pruning strategies}. Through extensive experiments, we confirm the efficiency of our proposed DIVINE approach over both real and synthetic graphs.

cs.DB↗

arXiv2025

FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is vulnerable to poisoning attacks, especially backdoor attacks. By using poisoned data for local training or directly changing the model parameters, attackers can easily inject backdoors into the model, which can trigger the model to make misclassification of targeted patterns in images. To address these issues, we propose a novel data-free trigger-generation-based defense approach based on the two characteristics of backdoor attacks: i) triggers are learned faster than normal knowledge, and ii) trigger patterns have a greater effect on image classification than normal class patterns. Our approach generates the images with newly learned knowledge by identifying the differences between the old and new global models, and filters trigger images by evaluating the effect of these generated images. By using these trigger images, our approach eliminates poisoned models to ensure the updated global model is benign. Comprehensive experiments demonstrate that our approach can defend against almost all the existing types of backdoor attacks and outperform all the seven state-of-the-art defense methods with both IID and non-IID scenarios. Especially, our approach can successfully defend against the backdoor attack even when 80\% of the clients are malicious.

cs.LG↗

arXiv2025

Gradients as an Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing

As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly suffer from two major problems: i) extremely high communication overhead due to massive item embeddings involved in recommendation systems, and ii) intolerably low training efficiency caused by the entanglement of both heterogeneous network environments and client devices. Although existing methods attempt to employ various compression techniques to reduce communication overhead, due to the parameter errors introduced by model compression, they inevitably suffer from model performance degradation. To simultaneously address the above problems, this paper presents a communication-efficient FedRec framework named FedRAS, which adopts an action-sharing strategy to cluster the gradients of item embedding into a specific number of model updating actions for communication rather than directly compressing the item embeddings. In this way, the cloud server can use the limited actions from clients to update all the items. Since gradient values are significantly smaller than item embeddings, constraining the directions of gradients (i.e., the action space) introduces smaller errors compared to compressing the entire item embedding matrix into a reduced space. To accommodate heterogeneous devices and network environments, FedRAS incorporates an adaptive clustering mechanism that dynamically adjusts the number of actions. Comprehensive experiments on well-known datasets demonstrate that FedRAS can reduce the size of communication payloads by up to 96.88%, while not sacrificing recommendation performance within various heterogeneous scenarios. We have open-sourced FedRAS at https://github.com/mastlab-T3S/FedRAS.

cs.LG↗

arXiv2025

VulStamp: Vulnerability Assessment using Large Language Model

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a substantial portion of detected vulnerabilities either possess low exploitability or would incur negligible impact in practical operational environments. Consequently, vulnerability severity assessment has emerged as a critical component in optimizing software development efficiency. Existing vulnerability assessment methods typically rely on manually crafted descriptions associated with source code artifacts. However, due to variability in description quality and subjectivity in intention interpretation, the performance of these methods is seriously limited. To address this issue, this paper introduces VulStamp, a novel intention-guided framework, to facilitate description-free vulnerability assessment. Specifically, VulStamp adopts static analysis together with Large Language Model (LLM) to extract the intention information of vulnerable code. Based on the intention information, VulStamp uses a prompt-tuned model for vulnerability assessment. Furthermore, to mitigate the problem of imbalanced data associated with vulnerability types, VulStamp integrates a Reinforcement Learning (RL)-based prompt-tuning method to train the assessment model.

cs.SE↗

arXiv2025

S3AND: Efficient Subgraph Similarity Search Under Aggregated Neighbor Difference Semantics (Technical Report)

For the past decades, the \textit{subgraph similarity search} over a large-scale data graph has become increasingly important and crucial in many real-world applications, such as social network analysis, bioinformatics network analytics, knowledge graph discovery, and many others. While previous works on subgraph similarity search used various graph similarity metrics such as the graph isomorphism, graph edit distance, and so on, in this paper, we propose a novel problem, namely \textit{subgraph similarity search under aggregated neighbor difference semantics} (S$^3$AND), which identifies subgraphs $g$ in a data graph $G$ that are similar to a given query graph $q$ by considering both keywords and graph structures (under new keyword/structural matching semantics). To efficiently tackle the S$^3$AND problem, we design two effective pruning methods, \textit{keyword set} and \textit{aggregated neighbor difference lower bound pruning}, which rule out false alarms of candidate vertices/subgraphs to reduce the S$^3$AND search space. Furthermore, we construct an effective indexing mechanism to facilitate our proposed efficient S$^3$AND query answering algorithm. Through extensive experiments, we demonstrate the effectiveness and efficiency of our S$^3$AND approach over both real and synthetic graphs under various parameter settings.

cs.DB↗

arXiv2025

R2Det: Exploring Relaxed Rotation Equivariance in 2D object detection

Group Equivariant Convolution (GConv) empowers models to explore underlying symmetry in data, improving performance. However, real-world scenarios often deviate from ideal symmetric systems caused by physical permutation, characterized by non-trivial actions of a symmetry group, resulting in asymmetries that affect the outputs, a phenomenon known as Symmetry Breaking. Traditional GConv-based methods are constrained by rigid operational rules within group space, assuming data remains strictly symmetry after limited group transformations. This limitation makes it difficult to adapt to Symmetry-Breaking and non-rigid transformations. Motivated by this, we mainly focus on a common scenario: Rotational Symmetry-Breaking. By relaxing strict group transformations within Strict Rotation-Equivariant group $\mathbf{C}_n$, we redefine a Relaxed Rotation-Equivariant group $\mathbf{R}_n$ and introduce a novel Relaxed Rotation-Equivariant GConv (R2GConv) with only a minimal increase of $4n$ parameters compared to GConv. Based on R2GConv, we propose a Relaxed Rotation-Equivariant Network (R2Net) as the backbone and develop a Relaxed Rotation-Equivariant Object Detector (R2Det) for 2D object detection. Experimental results demonstrate the effectiveness of the proposed R2GConv in natural image classification, and R2Det achieves excellent performance in 2D object detection with improved generalization capabilities and robustness. The code is available in \texttt{https://github.com/wuer5/r2det}.

cs.CV↗

arXiv2025

Optimal Approximate Matrix Multiplication over Sliding Windows

We explore the problem of approximate matrix multiplication (AMM) within the sliding window model, where algorithms utilize limited space to perform large-scale matrix multiplication in a streaming manner. This model has garnered increasing attention in the fields of machine learning and data mining due to its ability to handle time sensitivity and reduce the impact of outdated data. However, despite recent advancements, determining the optimal space bound for this problem remains an open question. In this paper, we introduce the DS-COD algorithm for AMM over sliding windows. This novel and deterministic algorithm achieves optimal performance regarding the space-error tradeoff. We provide theoretical error bounds and the complexity analysis for the proposed algorithm, and establish the corresponding space lower bound for the AMM sliding window problem. Additionally, we present an adaptive version of DS-COD, termed aDS-COD, which improves computational efficiency and demonstrates superior empirical performance. Extensive experiments conducted on both synthetic and real-world datasets validate our theoretical findings and highlight the practical effectiveness of our methods.

cs.DS↗

arXiv2025

FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control

Although Reinforcement Learning (RL)-based Traffic Signal Control (TSC) methods have been extensively studied, their practical applications still raise some serious issues such as high learning cost and poor generalizability. This is because the ``trial-and-error'' training style makes RL agents extremely dependent on the specific traffic environment, which also requires a long convergence time. To address these issues, we propose a novel Federated Imitation Learning (FIL)-based framework for multi-intersection TSC, named FitLight, which allows RL agents to plug-and-play for any traffic environment without additional pre-training cost. Unlike existing imitation learning approaches that rely on pre-training RL agents with demonstrations, FitLight allows real-time imitation learning and seamless transition to reinforcement learning. Due to our proposed knowledge-sharing mechanism and novel hybrid pressure-based agent design, RL agents can quickly find a best control policy with only a few episodes. Moreover, for resource-constrained TSC scenarios, FitLight supports model pruning and heterogeneous model aggregation, such that RL agents can work on a micro-controller with merely 16{\it KB} RAM and 32{\it KB} ROM. Extensive experiments demonstrate that, compared to state-of-the-art methods, FitLight not only provides a superior starting point but also converges to a better final solution on both real-world and synthetic datasets, even under extreme resource limitations.

cs.LG↗

arXiv2025

Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding

Hyperbolic spaces allow for more efficient modeling of complex, hierarchical structures, which is particularly beneficial in tasks involving multi-modal data. Although hyperbolic geometries have been proven effective for language-image pre-training, their capabilities to unify language, image, and 3D Point Cloud modalities are under-explored. We extend the 3D Point Cloud modality in hyperbolic multi-modal contrastive pre-training. Additionally, we explore the entailment, modality gap, and alignment regularizers for learning hierarchical 3D embeddings and facilitating the transfer of knowledge from both Text and Image modalities. These regularizers enable the learning of intra-modal hierarchy within each modality and inter-modal hierarchy across text, 2D images, and 3D Point Clouds. Experimental results demonstrate that our proposed training strategy yields an outstanding 3D Point Cloud encoder, and the obtained 3D Point Cloud hierarchical embeddings significantly improve performance on various downstream tasks.

cs.CV↗

arXiv2024

GCLS$^2$: Towards Efficient Community Detection Using Graph Contrastive Learning with Structure Semantics

Due to the power of learning representations from unlabeled graphs, graph contrastive learning (GCL) has shown excellent performance in community detection tasks. Existing GCL-based methods on the community detection usually focused on learning attribute representations of individual nodes, which, however, ignores structural semantics of communities (e.g., nodes in the same community should be structurally cohesive). Therefore, in this paper, we will consider the community detection under the community structure semantics and propose an effective framework for graph contrastive learning under structure semantics (GCLS$^2$) to detect communities. To seamlessly integrate interior dense and exterior sparse characteristics of communities with our contrastive learning strategy, we employ classic community structures to extract high-level structural views and design a structure semantic expression module to augment the original structural feature representation. Moreover, we formulate the structure contrastive loss to optimize the feature representation of nodes, which can better capture the topology of communities. To adapt to large-scale networks, we design a high-level graph partitioning (HGP) algorithm that minimizes the community detection loss for GCLS$^2$ online training. It is worth noting that we prove a lower bound on the training of GCLS$^2$ from the perspective of the information theory, explaining why GCLS$^2$ can learn a more accurate representation of the structure. Extensive experiments have been conducted on various real-world graph datasets and confirmed that GCLS$^2$ outperforms nine state-of-the-art methods, in terms of the accuracy, modularity, and efficiency of detecting communities.

cs.SI↗

arXiv2024

An Empirical Study of Vulnerability Detection using Federated Learning

Although Deep Learning (DL) methods becoming increasingly popular in vulnerability detection, their performance is seriously limited by insufficient training data. This is mainly because few existing software organizations can maintain a complete set of high-quality samples for DL-based vulnerability detection. Due to the concerns about privacy leakage, most of them are reluctant to share data, resulting in the data silo problem. Since enables collaboratively model training without data sharing, Federated Learning (FL) has been investigated as a promising means of addressing the data silo problem in DL-based vulnerability detection. However, since existing FL-based vulnerability detection methods focus on specific applications, it is still far unclear i) how well FL adapts to common vulnerability detection tasks and ii) how to design a high-performance FL solution for a specific vulnerability detection task. To answer these two questions, this paper first proposes VulFL, an effective evaluation framework for FL-based vulnerability detection. Then, based on VulFL, this paper conducts a comprehensive study to reveal the underlying capabilities of FL in dealing with different types of CWEs, especially when facing various data heterogeneity scenarios. Our experimental results show that, compared to independent training, FL can significantly improve the detection performance of common AI models on all investigated CWEs, though the performance of FL-based vulnerability detection is limited by heterogeneous data. To highlight the performance differences between different FL solutions for vulnerability detection, we extensively investigate the impacts of different configuration strategies for each framework component of VulFL. Our study sheds light on the potential of FL in vulnerability detection, which can be used to guide the design of FL-based solutions for vulnerability detection.

cs.SE↗