With the significant increase of communication network scales, intelligent Network Operation and Maintenance (NOM) becomes essential. Knowledge Graphs (KGs) are a key enabler for intelligent NOM, and Relational Triple Extraction (RTE) plays a critical role in KG construction. However, most existing RTE researches rely on general-domain corpora, with limited exploration into the specialized domain. In this paper, we identify a novel challenge in Chinese NOM corpus —Segmented Entity, which has garnered little attention in prior works. To address it, this paper proposes an Entity-level Autoregressive RTE (EARTE) method, which incorporates an innovative Segmented-BIO (Begin, Inside, Outside) tagging scheme. Furthermore, we construct the CMIM23-NOM1-RA, the first high-quality restricted domain RTE dataset for NOM. Throughout the experimentation, we meticulously reproduce all baselines and provide a comprehensive analysis. The results show that EARTE achieves the best performance on CMIM23-NOM1-RA. EARTE’s F1 scores surpass those of the best-performing baselines by 0.4%, 2.7%, and 0.8% under the strict criterion, the lenient criterion, and the setting focusing only on segmented entities, respectively. Finally, our codes, dataset, and reproduction guidelines are publicly available at: https://github.com/JYzzzzzz/PEAR-RTE.

Human action understanding is crucial for the advancement of multimodal systems. While recent developments, driven by powerful large language models (LLMs), aim to be general enough to cover a wide range of categories, they often overlook the need for more specific capabilities. In this work, we address the more challenging task of Fine-grained Action Recognition (FAR), which focuses on detailed semantic labels within shorter temporal duration (e.g., ``salto backward tucked with 1 turn"). Given the high costs of annotating fine-grained labels and the substantial data needed for fine-tuning LLMs, we propose to adopt semi-supervised learning (SSL). Our framework, SeFAR, incorporates several innovative designs to tackle these challenges. Specifically, to capture sufficient visual details, we construct Dual-level temporal elements as more effective representations, based on which we design a new strong augmentation strategy for the Teacher-Student learning paradigm through involving moderate temporal perturbation. Furthermore, to handle the high uncertainty within the teacher model's predictions for FAR, we propose the Adaptive Regulation to stabilize the learning process. Experiments show that SeFAR achieves state-of-the-art performance on two FAR datasets, FineGym and FineDiving, across various data scopes, as well as two classical coarse-grained datasets, UCF101 and HMDB51. Further analysis and ablation studies validate the effectiveness of our designs. Additionally, we show that the features extracted by SeFAR could largely promote the ability of multimodal models to understand fine-grained and domain-specific semantics.

Efficient lightweight neural networks are with increasing attention due to their faster reasoning speed and easier deployment on mobile devices. However, existing video pre-trained models still focus on the common ViT architecture with high latency, and few works attempt to build efficient architecture on mobile devices. This paper bridges this gap by introducing temporal structural reparameterization into an efficient image-text model and training it on a large-scale high-quality video-text dataset, resulting in an efficient video-text model that can run on mobile devices with strong zero-shot classification and retrieval capabilities, termed as MobileViCLIP. In particular, in terms of inference speed on mobile devices, our MobileViCLIP-Small is 55.4x times faster than InternVideo2-L14 and 6.7x faster than InternVideo2-S14. In terms of zero-shot retrieval performance, our MobileViCLIP-Small obtains similar performance as InternVideo2-L14 and obtains 6.9\% better than InternVideo2-S14 on MSR-VTT. The code is available at https://github.com/MCG-NJU/MobileViCLIP.

Communities, formed by a subset of vertices that are densely connected to each other and loosely connected to outside community members, widely exist to represent functional modules in real-world complex systems. Most existing community detection and search methods aim at finding communities at one single level, neglecting the natural properties of overlapping and hierarchy in communities. Therefore, the discovery of hierarchical graph clustering (HGC) to find communities at different levels, which is particularly useful in many applications. However, existing HGC studies suffer from two significant limitations: 1) inefficiency over large-scale networks, and 2) generating too many levels of community hierarchy without distinguishing the hierarchy differences. To address the above limitations, we revisit the problem of hierarchical graph clustering and formulate the problem based on our proposed three important properties. To tackle it, we propose theoretical-guaranteed fast solutions, in terms of algorithm complexity and hierarchy levels. We first formulate our HGC problem to admit three key properties of hierarchical communities. Based on the natural hierarchical structure of$k$-core, we develop a simple and importantly useful technique of core propagation. The key idea of core propagation is to take each$k$-core as one seed of hierarchical communities and find disjoint communities within$k$-core using a linear-time algorithm of label propagation. We propose two core propagation approaches of top-down and bottom-up algorithms, in terms of different search directions of$k$-cores by increment and decrement on$k$, respectively. The top-down method can find a given level of hierarchical communities in$O(t m)$time, where$t$is an input of hierarchy levels and$m$is the graph size. To dismiss the hardness of users' input hierarchy parameter$t$, the bottom-up algorithm is equipped with a well-designed strategy of auto-adjusting hierarchical levels based on the graph structure itself. We also develop the coreness weight-based label propagation to ensure the accurate label voting of compressed communities at low levels. The bottom-up method runs fast in$O(m \log \delta(G))$, where$\log \delta(G)$is a small value of the maximum coreness in graph$G$. Extensive experiments conducted on real-world graphs with ground-truth HGCs validate the effectiveness and efficiency of our proposed core propagation methods against state-of-the-art methods. Two case studies on the world-wide flight network and the Hong Kong road network demonstrate the particular usage of our HGC methods.

We present LongVPO, a novel two‑stage Direct Preference Optimization framework that enables short‑context vision‑language models to robustly understand ultra‑long videos without any long‑video annotations. In Stage 1, we synthesize preference triples by anchoring questions to individual short clips, interleaving them with distractors, and applying visual‑similarity and question‑specificity filtering to mitigate positional bias and ensure unambiguous supervision. We also approximate the reference model’s scoring over long contexts by evaluating only the anchor clip, reducing computational overhead. In Stage 2, we employ a recursive captioning pipeline on long videos to generate scene-level metadata, and then use a large language model to craft multi-segment reasoning queries and dispreferred responses, aligning the model's preferences through multi-segment reasoning tasks. With only 16K synthetic examples and no costly human labels, \model{} outperforms the state‑of‑the‑art open‑source models on multiple long‑video benchmarks, while maintaining strong short‑video performance (e.g., on MVBench), offering a scalable paradigm for efficient long‑form video understanding.

Network Operation and Maintenance (NOM) is an important part of the IT and telecommunications infrastructure. To improve the efficiency of NOM personnel, predict base station alarms, and classify base stations more precisely, we build a new labeled time series dataset, called BSAlarm, which collects 1000 different time series from processed real-world network alarm log data. Furthermore, we develop a NOM pipeline that employs B-spline interpolation alongside the moving average method to create and utilize this dataset for both long- and short-time series forecasting (LTSF), as well as base station classification tasks. Unlike prior NOM methods, our pipeline is centered on the generation of time series data, thereby enhancing alarm prediction performance and the visualization of changes under base station alarm conditions. Extensive experiments show that the proposed BSAlarm dataset and pipeline achieve remarkable results on time-series-data-based NOM.

Inter-cell interference poses a significant challenge to the performance and reliability of cellular networks due to the complex spatial and temporal relationships between network nodes. Addressing this issue requires accurate prediction and assessment of interference. This paper presents a novel solution leveraging the strengths of a weighted graph convolutional network (WGCN) combined with graph coloring techniques. Specifically, we propose a WGCN-based interference estimation model to accurately derive the real-time inter-cell interference. Then, a graph multi-coloring problem is considered for the interference coordination. To address the color collision between cells and the color (i.e. spectrum resources) requirement of individual cells in the graph coloring problem, we propose a WGCN-assisted graph multi-coloring (WGCN-GMC) algorithm to allocate spectrum resources rationally. Simulation results demonstrate that our approach significantly enhances interference coordination, and achieves an impressive average improvement of 58.2 % compared to the traditional GMC algorithm leading to improved overall network performance.

To analyze the discrimination and treatment of "Cold-Dampness Depression Lung Syndrome" of COVID-19 in TCM classics. Methods: Using the mathematical statistics and data mining methods to sort and analyze information of prescriptions treating "Cold-Dampness Depression Lung Syndrome" of COVID-19 in TCM classics. Results: 50 ancient prescriptions with therapeutic effects were selected, contain contain 125 traditional Chinese medicines, and the top 5 are Gancao (Glycyrrhizae Radix Rhizoma), Banxia(Pinelliae Rhizoma), Renshen (Ginseng Radix Et Rhizoma), Baizhu(Atractylodis Macrocephalae Rhizoma) and Chenpi(Citri Reticulatae Pericarpium) in order of frequency of use. The meridians of the medicines are mainly lung meridian, spleen meridian and stomach meridian, and the properties of the medicines are mostly warm, followed by mlid and lukewarm. The main medicinal pairs are Jiegeng (platycodonis Radix)-Gancao (Glycyrrhizae Radix Rhizoma), Baishao (Paeoniae Radix Alba)-Gancao (Glycyrrhizae Radix Rhizoma),Mahuang (Ephedrae Herba)-Gancao (Glycyrrhizae Radix Rhizoma),Chuanxiong (Chuanxiong Rhizoma)- Gancao (Glycyrrhizae Radix Rhizoma) and Cangnzhu (Atractylodis Rhizoma)-Gancao (Glycyrrhizae Radix Rhizoma).Conclusion: By analysing the ancient prescriptions with potential treatment for "Cold-Dampness Depression Lung Syndrome" of COVID-19, we found high-frequency medicines and medicinal pairs, and had a more comprehensive understanding of the treatment of COVID-19, can provide a reference for the research of COVID-19 specific medicines.

Objective Using literature data mining methods, we analyzed the frequency of medication, combinations of drugs, and so on in the treatment of goiter disease with ancient classic prescriptions. We aimed to uncover the core combinations and new prescriptions for treating goiter; s We searched the "Ancient Classic Prescription Database" for literature related to the treatment of goiter, selected the prescriptions for treating goiter, entered them into the medical case cloud platform of ancient and modern times, and used rule analysis, cluster analysis, and other data mining methods to analyze the rules of prescription combination. Results The study finally included 145 prescriptions. The results of drug frequency statistics showed that the use frequency of kelp, seaweed, and Pinellia was relatively high. The analysis of Chinese medicine properties revealed that cold and warm medicines were used frequently, as were bitter, pungent, and salty medicines. Medicines entering the stomach, liver, and kidney meridians were used the most. The results of association rule analysis and cluster analysis revealed the combination relationship and classification of Chinese medicines. Complex network analysis identified the core prescription composition for treating goiter in ancient classic prescriptions, including kelp, seaweed, and Pinellia. Conclusion: This study analyzed the treatment of goiter with ancient classic prescriptions through data mining and found that kelp, seaweed, and Pinellia might be the core combination for treating goiter. The research results can provide a reference for the clinical practice of traditional Chinese medicine in treating goiter.

Objective: To analyze the differentiation and treatment principles of Swollen-head Infection in TCM classics. Methods: Ancient medical case data related to warm diseases were selected as the data source, and the standard principles of data extraction were formulated. Data mining methods such as mathematical statistics, factor analysis, cluster analysis, and association rules were used to systematically sort out and analyze the etiology, location, syndrome, treatment, formulations and other information of Swollen-head Infection. Results: Swollen-head Infection is primarily attributed to pathogenic wind and heat toxins. The significance of "Li Qi" (Epidemic pathogen) should be emphasized.The disease primarily affects the head, and the pathogenic factors tend to linger in the lung-defense. The clinical manifestations are closely related to the affected area of the head, often accompanied by other systemic symptoms. The treatment approach commonly involves combining internal and external therapies. Combinations of herbs such as Xuanshen (Scrophulariae Radix)-Lianqiao (Forsythiae Fructus), Xuanshen (Scrophulariae Radix)-Huangqin(Scutellariae Radix), Jiegeng(Platycodonis Radix)-Lianqiao (Forsythiae Fructus), Jiegeng(Platycodonis Radix)-Huangqin(Scutellariae Radix), Chaihu(Bupleuri Radix)- Jiegeng(Platycodonis Radix), and Chaihu(Bupleuri Radix)- Huanglian(Coptidis Rhizoma) are notable for their abilities to clear heat, detoxify, disperse wind, and eliminate pathogenic factors. Additionally, Puji Xiaodu Yin and its modifications are considered essential medications for treating Swollen-head Infection. Conclusion: Through the data mining of the rules of syndrome and prescription of Swollen-head Infection in ancient books of warm diseases, to provide reference for the differentiation and treatment of head and face swelling and poison infectious diseases.

The early stage of brucellosis belongs to the category of latent temperature disease in traditional Chinese medicine, and the symptom is damp-heat epidemic pathogen. But later to joint pain, soreness and weakness of waist and knees, fatigue, joint pain, night sweats, etc., mainly in the joint, belongs to the liver and kidney deficiency, qi and blood deficiency, spleen wet turbidity syndrome, belongs to the category of traditional Chinese medicine rheumatism heat arthralgia syndrome, etiology and pathogenesis due to ' winter does not store essence, spring must disease temperature ' within the virtual cause. Based on the syndrome differentiation of traditional Chinese medicine, Duhuo Jisheng Decoction combined with Simiao Pill was used to treat liver and kidney, nourish qi and blood, and eliminate dampness and turbidity, so as to achieve the purpose of strengthening the body and eliminating evil, restoring healthy qi and eliminating evil qi. To provide reference for the treatment of infectious diseases such as brucellosis.

Objective; To analyze the discrimination and treatment of acute larynx ulcer in TCM classics. Methods: Using the mathematical statistics and data mining methods to sort and analyze information of the scarlet fever in TCM classics, such as etiology, disease-bit, treatment and formulas. Results: The causes of the scarlet fever involved warms up when poison, weakened body resistance and pidemic pathogen with li gas, and its site of cerebral apoplexy located in throat, skin and stomach. TCM syndrome of the scarlet fever included pathogenic factors invade lung and surface, toxic obstructing qi aspect, pathogenic factors invade the ying blood and pathogenic factors invade liver and kidney. For the treatment of the scarlet fever, the main method is clearing heat and detoxification, and external treatment is emphasized, such as external application, laryngeal blowing and removing corruption. Niuhuang (Bovis Calculus)-Zhenzhu (Margarita), Bingpian (Borneolum Syntheticum)-Daqingye (Isatidis Folium), Niuxi (Achyranthis Bidentatae Radix)-Tuniuxigen (Achyranthes aspera), Bingpian (Borneolum Syntheticum)-Niuhuang (Bovis Calculus), Bingpian (Borneolum Syntheticum)-Xionghuang (Realgar), Bingpian (Borneolum Syntheticum)-Shexiang (Moschus) combination has the characteristics of scarlet fever treatment. Conclusion: By summarizing and excavating the rules of syndrome differentiation and treatment of scarlet fever, it can provide a reference for the treatment of modern acute respiratory infectious diseases.

BACKGROUND - Predicting defect-prone software components is an economically important activity and so has received a good deal of attention. However, making sense of the many, and sometimes seemingly inconsistent, results is difficult. OBJECTIVE - We propose and evaluate a general framework for software defect prediction that supports 1) unbiased and 2) comprehensive comparison between competing prediction systems. METHOD - The framework is comprised of 1) scheme evaluation and 2) defect prediction components. The scheme evaluation analyzes the prediction performance of competing learning schemes for given historical data sets. The defect predictor builds models according to the evaluated learning scheme and predicts software defects with new data according to the constructed model. In order to demonstrate the performance of the proposed framework, we use both simulation and publicly available software defect data sets. RESULTS - The results show that we should choose different learning schemes for different data sets (i.e., no scheme dominates), that small details in conducting how evaluations are conducted can completely reverse findings, and last, that our proposed framework is more effective and less prone to bias than previous approaches. CONCLUSIONS - Failure to properly or fully evaluate a learning scheme can be misleading; however, these problems may be overcome by our proposed framework.

A new associative classification algorithm based on weighted voting (ACWV) is presented. ACWV takes advantage of two methods: the optimal rule method preferring high-quality rules and the voting method considering the majority of the rules. Moreover, the method takes into account both the length and convictions of rules to calculate their weights. First, ACWV builds a class-count FP-tree (called CCFP-tree) from the given historical data. After that, the weighted voting result for a new instance can be obtained from the CCFP-tree directly without storing, retrieving and sorting rules explicitly. The label of the class with maximal sum of weighted votes is then that of the new instance. Results of the experiments with 36 data sets selected from the UCI machine learning repository show that the proposed method has its advantages in comparison with previous methods in terms of classification accuracy.