arXiv subjects

Yudong Liu

Publications and source records attributed to Yudong Liu.

45 records · Page 3Linked to original sources

arXiv2022

UniParser: A Unified Log Parser for Heterogeneous Log Data

Logs provide first-hand information for engineers to diagnose failures in large-scale online service systems. Log parsing, which transforms semi-structured raw log messages into structured data, is a prerequisite of automated log analysis such as log-based anomaly detection and diagnosis. Almost all existing log parsers follow the general idea of extracting the common part as templates and the dynamic part as parameters. However, these log parsing methods, often neglect the semantic meaning of log messages. Furthermore, high diversity among various log sources also poses an obstacle in the generalization of log parsing across different systems. In this paper, we propose UniParser to capture the common logging behaviours from heterogeneous log data. UniParser utilizes a Token Encoder module and a Context Encoder module to learn the patterns from the log token and its neighbouring context. A Context Similarity module is specially designed to model the commonalities of learned patterns. We have performed extensive experiments on 16 public log datasets and our results show that UniParser outperperforms state-of-the-art log parsers by a large margin.

cs.SE↗

arXiv2022

Further q-analogues of the (G.2) Supercongruence of Van Hamme

In 2015, Swisher generalized the (G.2) supercongruence of Van Hamme to the modulus p^4. In this paper, we first propose two q-analogues of Swisher's supercongruence and then a new q-congruence with parameters %which including several different q-analogues of Swisher's supercongruence is present.

math.CO↗

arXiv2021

Some q-supercongruences from Rahman's summation formula

Inspired by the recent work on $q$-congruences and the quadratic summation formula of Rahman, we provide some new $q$-supercongruences. By taking $q\to 1$ in one of our results, we obtain a new Ramanujan-type supercongruence, which has the same right-hand side as Van Hamme's (G.2) supercongruence for $p\equiv 1 \pmod 4$. We also formulate some related challenging conjectures on supercongruences and $q$-supercongruences.

math.CO↗

arXiv2020

$q$-Supercongruences from the $q$-Saalschütz identity

In terms of the $q$-Saalschütz identity and the Chinese remainder theorem for coprime polynomials, we establish some $q$-supercongruences modulo the third power of a cyclotomic polynomial. In particular, we give a $q$-analogue of a formula due to Long and Ramakrishna [Adv. Math. 290 (2016), 773--808].

math.CO↗

arXiv2020

QSAN: A Quantum-probability based Signed Attention Network for Explainable False Information Detection

False information detection on social media is challenging as it commonly requires tedious evidence-collecting but lacks available comparative information. Clues mined from user comments, as the wisdom of crowds, could be of considerable benefit to this task. However, it is non-trivial to capture the complex semantics from the contents and comments in consideration of their implicit correlations. Although deep neural networks have good expressive power, one major drawback is the lack of explainability. In this paper, we focus on how to learn from the post contents and related comments in social media to understand and detect the false information more effectively, with explainability. We thus propose a Quantum-probability based Signed Attention Network (QSAN) that integrates the quantum-driven text encoding and a novel signed attention mechanism in a unified framework. QSAN is not only able to distinguish important comments from the others, but also can exploit the conflicting social viewpoints in the comments to facilitate the detection. Moreover, QSAN is advantageous with its explainability in terms of transparency due to quantum physics meanings and the attention weights. Extensive experiments on real-world datasets show that our approach outperforms state-of-the-art baselines and can provide different kinds of user comments to explain why a piece of information is detected as false.

cs.SI↗

arXiv2020

q-analogues of the G.2 Supercongruence of Van Hamme

Motivated by the recent research of congruences and $q$-congruences, we provide two different $q$-analogues of the (G.2) supercongruence of Van Hamme through the `creative microscoping' method, which was devised by Guo and Zudilin. It is a remarkable fact that this is the first time to give direct $q$-analogues of (G.2). In addition, we propose a conjecture related to Swisher's Dwork-type supercongruence (G.3).

math.NT↗

arXiv2019

CBNet: A Novel Composite Backbone Network Architecture for Object Detection

In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it. In this paper, we aim to achieve better detection performance by building a more powerful backbone from existing backbones like ResNet and ResNeXt. Specifically, we propose a novel strategy for assembling multiple identical backbones by composite connections between the adjacent backbones, to form a more powerful backbone named Composite Backbone Network (CBNet). In this way, CBNet iteratively feeds the output features of the previous backbone, namely high-level features, as part of input features to the succeeding backbone, in a stage-by-stage fashion, and finally the feature maps of the last backbone (named Lead Backbone) are used for object detection. We show that CBNet can be very easily integrated into most state-of-the-art detectors and significantly improve their performances. For example, it boosts the mAP of FPN, Mask R-CNN and Cascade R-CNN on the COCO dataset by about 1.5 to 3.0 percent. Meanwhile, experimental results show that the instance segmentation results can also be improved. Specially, by simply integrating the proposed CBNet into the baseline detector Cascade Mask R-CNN, we achieve a new state-of-the-art result on COCO dataset (mAP of 53.3) with single model, which demonstrates great effectiveness of the proposed CBNet architecture. Code will be made available on https://github.com/PKUbahuangliuhe/CBNet.

cs.CV↗

arXiv2015

Concept for a Future Super Proton-Proton Collider

Following the discovery of the Higgs boson at LHC, new large colliders are being studied by the international high-energy community to explore Higgs physics in detail and new physics beyond the Standard Model. In China, a two-stage circular collider project CEPC-SPPC is proposed, with the first stage CEPC (Circular Electron Positron Collier, a so-called Higgs factory) focused on Higgs physics, and the second stage SPPC (Super Proton-Proton Collider) focused on new physics beyond the Standard Model. This paper discusses this second stage.

physics.acc-ph↗

arXiv2015

Impedance Measurements of the Extraction Kicker System for the Rapid Cycling Synchrotron of China Spallation Neutron Source

The fast extraction kicker system is one of the most important accelerator components, whose inner structure will be the main source of the impedance in the RCS. It is necessary to understand the kicker impedance before its installation into the tunnel. The conventional and improved wire methods are employed for the benchmarking impedance measurement results. The simulation and measurements confirm that the window-frame ferrite geometry and the end plate are the important structures causing the coupling impedance. The total impedance of the eight modules systems is determined by the scaling law from the measurement and the impedance measurement of the kicker system is summarized.

physics.acc-ph↗