arXiv subjects

Jing Liu

Publications and source records attributed to Jing Liu.

At least 289 records · Page 16Linked to original sources

arXiv2025

Oriented diameter of the complete tripartite graph (III)

Given a bridgeless graph $G$, let $\mathbb{D}(G)$ be the set of all strong orientations of $G$, and define the oriented diameter $f(G)$ of $G$ to be the minimum of diameters $diam(D)$ among all the strong orientations $D\in \mathbb{D}(G)$, i.e., $f(G)=\min\{diam(D)\mid D\in \mathbb{D}(G)\}$. In this paper, we determine the oriented diameter of complete tripartite graph $K(3,p,q)$ for $p\geqslant 5$. Combining with the previous results, the oriented diameter of complete tripartite graph $K(3,p,q)$ are known.

math.CO↗

arXiv2025

Efficient Optimization of Variational Autoregressive Networks with Natural Gradient

Estimating free energy is a fundamental problem in statistical mechanics. Recently, machine-learning-based methods, particularly the variational autoregressive networks (VANs) have been proposed to minimize variational free energy and to approximate the Boltzmann distribution. VAN enjoys notable advantages, including the exact computation of the normalized joint distribution and fast sampling, which are critical features often missing in Markov chain Monte Carlo algorithms. However, VAN also faces significant computational challenges. These include difficulties in the optimization of variational free energy in a complicated parameter space and slow convergence of learning. In this work, we introduce an optimization technique based on natural gradients to the VAN framework, namely ng-VAN, to enhance the learning efficiency and accuracy of the conventional VAN. The method has computational complexity cubic in the batch size rather than in the number of model parameters, hence it can be efficiently implemented for a large VAN model. We carried out extensive numerical experiments on the Sherrington-Kirkpatrick model, spin glasses on random graphs, and the two-dimensional Ising model. Our results indicate that compared with the conventional VAN, ng-VAN significantly improves the accuracy in estimating free energy and converges much faster with shorter learning time. This allows extending the VAN framework's applicability to challenging statistical mechanics problems that were previously not accessible.

cond-mat.stat-mech↗

arXiv2025

NSPG-Miner: Mining Repetitive Negative Sequential Patterns

Sequential pattern mining (SPM) with gap constraints (or repetitive SPM or tandem repeat discovery in bioinformatics) can find frequent repetitive subsequences satisfying gap constraints, which are called positive sequential patterns with gap constraints (PSPGs). However, classical SPM with gap constraints cannot find the frequent missing items in the PSPGs. To tackle this issue, this paper explores negative sequential patterns with gap constraints (NSPGs). We propose an efficient NSPG-Miner algorithm that can mine both frequent PSPGs and NSPGs simultaneously. To effectively reduce candidate patterns, we propose a pattern join strategy with negative patterns which can generate both positive and negative candidate patterns at the same time. To calculate the support (frequency of occurrence) of a pattern in each sequence, we explore a NegPair algorithm that employs a key-value pair array structure to deal with the gap constraints and the negative items simultaneously and can avoid redundant rescanning of the original sequence, thus improving the efficiency of the algorithm. To report the performance of NSPG-Miner, 11 competitive algorithms and 11 datasets are employed. The experimental results not only validate the effectiveness of the strategies adopted by NSPG-Miner, but also verify that NSPG-Miner can discover more valuable information than the state-of-the-art algorithms. Algorithms and datasets can be downloaded from https://github.com/wuc567/Pattern-Mining/tree/master/NSPG-Miner.

cs.DB↗

arXiv2025

Oriented diameter of the complete tripartite graph (II)

For a graph $G$, let $\mathbb{D}(G)$ denote the set of all strong orientations of $G$, and the oriented diameter of $G$ is $f(G)=\min \{diam(D) \mid D \in \mathbb{D}(G)\}$, which is the minimum value of the diameters $diam(D)$ where $D \in \mathbb{D}(G)$. In this paper, we determine the oriented diameter of complete tripartite graphs $K(3,3, q)$ and $K(3,4, q)$, these are special cases that arise in determining the oriented diameter of $K(3, p, q)$.

math.CO↗

arXiv2025

Smoothed Embeddings for Robust Language Models

Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vulnerable to jailbreaking attacks that employ adversarial inputs that subvert alignment and induce harmful outputs. We propose the Randomized Embedding Smoothing and Token Aggregation (RESTA) defense, which adds random noise to the embedding vectors and performs aggregation during the generation of each output token, with the aim of better preserving semantic information. Our experiments demonstrate that our approach achieves superior robustness versus utility tradeoffs compared to the baseline defenses.

cs.LG↗

arXiv2025

Community-Aware Temporal Walks: Parameter-Free Representation Learning on Continuous-Time Dynamic Graphs

Dynamic graph representation learning plays a crucial role in understanding evolving behaviors. However, existing methods often struggle with flexibility, adaptability, and the preservation of temporal and structural dynamics. To address these issues, we propose Community-aware Temporal Walks (CTWalks), a novel framework for representation learning on continuous-time dynamic graphs. CTWalks integrates three key components: a community-based parameter-free temporal walk sampling mechanism, an anonymization strategy enriched with community labels, and an encoding process that leverages continuous temporal dynamics modeled via ordinary differential equations (ODEs). This design enables precise modeling of both intra- and inter-community interactions, offering a fine-grained representation of evolving temporal patterns in continuous-time dynamic graphs. CTWalks theoretically overcomes locality bias in walks and establishes its connection to matrix factorization. Experiments on benchmark datasets demonstrate that CTWalks outperforms established methods in temporal link prediction tasks, achieving higher accuracy while maintaining robustness.

cs.LG↗

arXiv2025

Tree Models Machine Learning to Identify Liquid Metal based Alloy Superconductor

Superconductors, which are crucial for modern advanced technologies due to their zero-resistance properties, are limited by low Tc and the difficulty of accurate prediction. This article made the initial endeavor to apply machine learning to predict the critical temperature (Tc) of liquid metal (LM) alloy superconductors. Leveraging the SuperCon dataset, which includes extensive superconductor property data, we developed a machine learning model to predict Tc. After addressing data issues through preprocessing, we compared multiple models and found that the Extra Trees model outperformed others with an R2 of 0.9519 and an RMSE of 6.2624 K. This model is subsequently used to predict Tc for LM alloys, revealing In0.5Sn0.5 as having the highest Tc at 7.01 K. Furthermore, we extended the prediction to 2,145 alloys binary and 45,670 ternary alloys across 66 metal elements and promising results were achieved. This work demonstrates the advantages of tree-based models in predicting Tc and would help accelerate the discovery of high-performance LM alloy superconductors in the coming time.

cond-mat.supr-con↗

arXiv2025

Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Datasets

Understanding and analyzing the spatial semantics and structure of forests is essential for accurate forest resource monitoring and ecosystem research. However, the lack of large-scale and annotated datasets has limited the widespread use of advanced intelligent techniques in this field. To address this challenge, a fully automated synthetic data generation and processing framework based on the concepts of Digital Cousins and Simulation-to-Reality (Sim2Real) is proposed, offering versatility and scalability to any size and platform. Using this process, we created the Boreal3D, the world's largest forest point cloud dataset. It includes 1000 highly realistic and structurally diverse forest plots across four different platforms, totaling 48,403 trees and over 35.3 billion points. Each point is labeled with semantic, instance, and viewpoint information, while each tree is described with structural parameters such as diameter, crown width, leaf area, and total volume. We designed and conducted extensive experiments to evaluate the potential of Boreal3D in advancing fine-grained 3D forest structure analysis in real-world applications. The results demonstrate that with certain strategies, models pre-trained on synthetic data can significantly improve performance when applied to real forest datasets. Especially, the findings reveal that fine-tuning with only 20% of real-world data enables the model to achieve performance comparable to models trained exclusively on entire real-world data, highlighting the value and potential of our proposed framework. The Boreal3D dataset, and more broadly, the synthetic data augmentation framework, is poised to become a critical resource for advancing research in large-scale 3D forest scene understanding and structural parameter estimation.

cs.CV↗

arXiv2025

VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset

In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation. Different from widely-studied vision-language pretraining models, VALOR jointly models relationships of vision, audio and language in an end-to-end manner. It contains three separate encoders for single modality representations, and a decoder for multimodal conditional text generation. We design two pretext tasks to pretrain VALOR model, including Multimodal Grouping Alignment (MGA) and Multimodal Grouping Captioning (MGC). MGA projects vision, language and audio to the same common space, building vision-language, audio-language and audiovisual-language alignment simultaneously. MGC learns how to generate text tokens in conditions of vision, audio or their both. To promote vision-audio-language pretraining research, we construct a large-scale high-quality tri-modality dataset named VALOR-1M, which contains 1M audiable videos with human annotated audiovisual captions. Extensive experiments show that VALOR can learn strong multimodal correlations and be generalized to various downstream tasks (e.g., retrieval, captioning and question answering), with different input modalities (e.g., vision-language, audio-language and audiovisual-language). VALOR achieves new state-of-the-art performances on series of public cross-modality benchmarks. Code and data are available at project page https://casia-iva-group.github.io/projects/VALOR.

cs.LG↗

arXiv2025

CompetitorFormer: Competitor Transformer for 3D Instance Segmentation

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and IoU scores to select the top prediction as the final outcome. However, it has been observed that the current models employ a fixed and higher number of queries than the instances present within a scene. In such instances, multiple queries predict the same instance, yet only a single query is ultimately optimized. The close scores of queries in the lower-level decoders make it challenging for the dominant query to distinguish itself rapidly, which ultimately impairs the model's accuracy and convergence efficiency. This phenomenon is referred to as inter-query competition. To address this challenge, we put forth a series of plug-and-play competition-oriented designs, collectively designated as the CompetitorFormer, with the aim of reducing competition and facilitating a dominant query. Experiments showed that integrating our designs with state-of-the-art frameworks consistently resulted in significant performance improvements in 3D instance segmentation across a range of datasets.

cs.CV↗

arXiv2024

DECN: Evolution Inspired Deep Convolution Network for Black-box Optimization

Evolutionary algorithms (EAs) have emerged as a powerful framework for optimization, especially for black-box optimization. Existing evolutionary algorithms struggle to comprehend and effectively utilize task-specific information for adjusting their optimization strategies, leading to subpar performance on target tasks. Moreover, optimization strategies devised by experts tend to be highly biased. These challenges significantly impede the progress of the field of evolutionary computation. Therefore, this paper first introduces the concept of Automated EA: Automated EA exploits structure in the problem of interest to automatically generate update rules (optimization strategies) for generating and selecting potential solutions so that it can move a random population near the optimal solution. However, current EAs cannot achieve this goal due to the poor representation of the optimization strategy and the weak interaction between the optimization strategy and the target task. We design a deep evolutionary convolution network (DECN) to realize the move from hand-designed EAs to automated EAs without manual interventions. DECN has high adaptability to the target task and can obtain better solutions with less computational cost. DECN is also able to effectively utilize the low-fidelity information of the target task to form an efficient optimization strategy. The experiments on nine synthetics and two real-world cases show the advantages of learned optimization strategies over the state-of-the-art human-designed and meta-learning EA baselines. In addition, due to the tensorization of the operations, DECN is friendly to the acceleration provided by GPUs and runs 102 times faster than EA.

cs.NE↗

arXiv2024

Silencer: Robust Community Detection by Silencing of Noisy Pixels

Real-world networks carry all kinds of noise, resulting in numerous challenges for community detection. Further improving the performance and robustness of community detection has attracted significant attention. This paper considers edge noise, which causes edges in the network to be added or removed. Existing methods achieve graph denoising through link prediction or robustness in low eigenvectors. However, they are either limited in application scenarios or not determined for effectiveness. We find that the noisy pixel in the adjacency matrix has a certain proportion in the loss function, which makes the optimization of the community detection model seriously deviate from the correct direction. Thus, we design an flexible framework to silence the contribution of noisy pixels to loss function, called Silencer. We take the nonnegative matrix factorization (NMF) and deep NMF methods as examples since they are the prime models for community detection. We first prove the convergence of Silencer in NMF. Compared with existing methods, Silencer show top performance in six real-world networks with random noise, adversarial perturbation, and mixed noise. Moreover, Silencer works on random (ER), scale-free (BA), and small-world (WS) networks, and the improvement of Silencer is gradually insignificant in the order ER, BA, and WS networks.

cs.SI↗

arXiv2024

FedCross: Intertemporal Federated Learning Under Evolutionary Games

Federated Learning (FL) mitigates privacy leakage in decentralized machine learning by allowing multiple clients to train collaboratively locally. However, dynamic mobile networks with high mobility, intermittent connectivity, and bandwidth limitation severely hinder model updates to the cloud server. Although previous studies have typically addressed user mobility issue through task reassignment or predictive modeling, frequent migrations may result in high communication overhead. Overcoming this obstacle involves not only dealing with resource constraints, but also finding ways to mitigate the challenges posed by user migrations. We therefore propose an intertemporal incentive framework, FedCross, which ensures the continuity of FL tasks by migrating interrupted training tasks to feasible mobile devices. Specifically, FedCross comprises two distinct stages. In Stage 1, we address the task allocation problem across regions under resource constraints by employing a multi-objective migration algorithm to quantify the optimal task receivers. Moreover, we adopt evolutionary game theory to capture the dynamic decision-making of users, forecasting the evolution of user proportions across different regions to mitigate frequent migrations. In Stage 2, we utilize a procurement auction mechanism to allocate rewards among base stations, ensuring that those providing high-quality models receive optimal compensation. This approach incentivizes sustained user participation, thereby ensuring the overall feasibility of FedCross. Finally, experimental results validate the theoretical soundness of FedCross and demonstrate its significant reduction in communication overhead.

cs.LG↗

arXiv2024

M2OST: Many-to-one Regression for Predicting Spatial Transcriptomics from Digital Pathology Images

The advancement of Spatial Transcriptomics (ST) has facilitated the spatially-aware profiling of gene expressions based on histopathology images. Although ST data offers valuable insights into the micro-environment of tumors, its acquisition cost remains expensive. Therefore, directly predicting the ST expressions from digital pathology images is desired. Current methods usually adopt existing regression backbones along with patch-sampling for this task, which ignores the inherent multi-scale information embedded in the pyramidal data structure of digital pathology images, and wastes the inter-spot visual information crucial for accurate gene expression prediction. To address these limitations, we propose M2OST, a many-to-one regression Transformer that can accommodate the hierarchical structure of the pathology images via a decoupled multi-scale feature extractor. Unlike traditional models that are trained with one-to-one image-label pairs, M2OST uses multiple images from different levels of the digital pathology image to jointly predict the gene expressions in their common corresponding spot. Built upon our many-to-one scheme, M2OST can be easily scaled to fit different numbers of inputs, and its network structure inherently incorporates nearby inter-spot features, enhancing regression performance. We have tested M2OST on three public ST datasets and the experimental results show that M2OST can achieve state-of-the-art performance with fewer parameters and floating-point operations (FLOPs).

cs.CV↗

arXiv2024

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning

Due to the sensitivity of data, Federated Learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized FL, clients' communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges inherent in real-world scenarios. To tackle this issue, we propose a TRust-Aware clIent scheduLing mechanism called TRAIL, which assesses client states and contributions, enhancing model training efficiency through selective client participation. We focus on a semi-decentralized FL framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we propose an adaptive hidden semi-Markov model to estimate clients' communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7% in test accuracy and a reduction of 15.3% in training loss.

cs.LG↗

arXiv2024

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification

The efficiency of large vision-language models (LVLMs) is constrained by the computational bottleneck of the attention mechanism during the prefill phase and the memory bottleneck of fetching the key-value (KV) cache in the decoding phase, particularly in scenarios involving high-resolution images or videos. Visual content often exhibits substantial redundancy, resulting in highly sparse attention maps within LVLMs. This sparsity can be leveraged to accelerate attention computation or compress the KV cache through various approaches. However, most studies focus on addressing only one of these bottlenecks and do not adequately support dynamic adjustment of sparsity concerning distinct layers or tasks. In this paper, we present ZipVL, an efficient inference framework designed for LVLMs through a dynamic ratio allocation strategy of important tokens. This ratio is adaptively determined based on the layer-specific distribution of attention scores, rather than fixed hyper-parameters, thereby improving efficiency for less complex tasks while maintaining high performance for more challenging ones. Then we select important tokens based on their normalized attention scores and perform sparse attention mechanism solely on those important tokens, reducing the latency in the prefill phase. Tokens deemed less important will be discarded to reduce KV cache size, alleviating the memory bottleneck in the decoding phase. Our experiments demonstrate that ZipVL can accelerate the prefill phase by 2.3$\times$ and improve decoding throughput by 2.8$\times$, with a minimal accuracy reduction of only 0.5\% on VQAv2 benchmark over LLaVA-Next-13B model, effectively enhancing the generation efficiency of LVLMs.

cs.CV↗

arXiv2024

AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks

In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous graphs-simultaneously. This challenge has led to the manual design of GNNs tailored to specific graph types, but these approaches are limited by the high cost of labor and the constraints of expert knowledge, which cannot keep up with the rapid growth of graph data. To overcome these challenges, we propose AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. AutoSGNN unifies the search space for spectral GNNs by integrating large language models with evolutionary strategies to automatically generate architectures that adapt to various graph types. Extensive experiments on nine widely-used datasets, encompassing both homophilic and heterophilic graphs, demonstrate that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.

cs.LG↗

arXiv2024

Two Layer Walk: A Community-Aware Graph Embedding

Community structures are critical for understanding the mesoscopic organization of networks, bridging local and global patterns. While methods such as DeepWalk and node2vec capture local positional information through random walks, they fail to preserve community structures. Other approaches like modularized nonnegative matrix factorization and evolutionary algorithms address this gap but are computationally expensive and unsuitable for large-scale networks. To overcome these limitations, we propose Two Layer Walk (TLWalk), a novel graph embedding algorithm that incorporates hierarchical community structures. TLWalk balances intra- and inter-community relationships through a community-aware random walk mechanism without requiring additional parameters. Theoretical analysis demonstrates that TLWalk effectively mitigates locality bias. Experiments on benchmark datasets show that TLWalk outperforms state-of-the-art methods, achieving up to 3.2% accuracy gains for link prediction tasks. By encoding dense local and sparse global structures, TLWalk proves robust and scalable across diverse networks, offering an efficient solution for network analysis.

cs.SI↗