المؤلفون: Xie, Jiakuan, Cao, Pengfei, Chen, Yuheng, Chen, Yubo, Liu, Kang, Zhao, Jun

مصطلحات موضوعية: Computer Science - Computation and Language

الوصف: Knowledge editing aims to adjust the knowledge within large language models (LLMs) to prevent their responses from becoming obsolete or inaccurate. However, existing works on knowledge editing are primarily conducted in a single language, which is inadequate for multilingual language models. In this paper, we focus on multilingual knowledge editing (MKE), which requires propagating updates across multiple languages. This necessity poses a significant challenge for the task. Furthermore, the limited availability of a comprehensive dataset for MKE exacerbates this challenge, hindering progress in this area. Hence, we introduce the Multilingual Knowledge Editing Benchmark (MKEB), a novel dataset comprising 12 languages and providing a complete evaluation framework. Additionally, we propose a method that enhances Multilingual knowledge Editing with neuron-Masked Low-Rank Adaptation (MEMLA). Specifically, we identify two categories of knowledge neurons to improve editing precision. Moreover, we perform LoRA-based editing with neuron masks to efficiently modify parameters and facilitate the propagation of updates across multiple languages. Experiments demonstrate that our method outperforms existing baselines and significantly enhances the multi-hop reasoning capability of the edited model, with minimal impact on its downstream task performance. The dataset and code will be made publicly available.

الوصول الحر: http://arxiv.org/abs/2406.11566Test

المؤلفون: Chen, Yuheng, Cao, Pengfei, Chen, Yubo, Liu, Kang, Zhao, Jun

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

الوصف: Large language models (LLMs) store extensive factual knowledge, but the mechanisms behind how they store and express this knowledge remain unclear. The Knowledge Neuron (KN) thesis is a prominent theory for explaining these mechanisms. This theory is based on the knowledge localization (KL) assumption, which suggests that a fact can be localized to a few knowledge storage units, namely knowledge neurons. However, this assumption may be overly strong regarding knowledge storage and neglects knowledge expression mechanisms. Thus, we re-examine the KL assumption and confirm the existence of facts that do not adhere to it from both statistical and knowledge modification perspectives. Furthermore, we propose the Query Localization (QL) assumption. (1) Query-KN Mapping: The localization results are associated with the query rather than the fact. (2) Dynamic KN Selection: The attention module contributes to the selection of KNs for answering a query. Based on this, we further propose the Consistency-Aware KN modification method, which improves the performance of knowledge modification. We conduct 39 sets of experiments, along with additional visualization experiments, to rigorously validate our conclusions.

الوصول الحر: http://arxiv.org/abs/2405.14117Test

المؤلفون: Chen, Yuheng, Cao, Pengfei, Chen, Yubo, Wang, Yining, Liu, Shengping, Liu, Kang, Zhao, Jun

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

الوصف: Large language models (LLMs) store extensive factual knowledge, but the underlying mechanisms remain unclear. Previous research suggests that factual knowledge is stored within multi-layer perceptron weights, and some storage units exhibit degeneracy, referred to as Degenerate Knowledge Neurons (DKNs). Despite the novelty and unique properties of this concept, it has not been rigorously defined or systematically studied. We first consider the connection weight patterns of MLP neurons and define DKNs from both structural and functional aspects. Based on this, we introduce the Neurological Topology Clustering method, which allows the formation of DKNs in any numbers and structures, leading to a more accurate DKN acquisition. Furthermore, inspired by cognitive science, we explore the relationship between DKNs and the robustness, evolvability, and complexity of LLMs. Our execution of 34 experiments under 6 settings demonstrates the connection between DKNs and these three properties. The code will be available soon.

الوصول الحر: http://arxiv.org/abs/2402.13731Test

المؤلفون: Wu, Baodong, Xia, Lei, Li, Qingping, Li, Kangyu, Chen, Xu, Guo, Yongqiang, Xiang, Tieyao, Chen, Yuheng, Li, Shigang

مصطلحات موضوعية: Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Artificial Intelligence

الوصف: Large language models (LLMs) with hundreds of billions or trillions of parameters, represented by chatGPT, have achieved profound impact on various fields. However, training LLMs with super-large-scale parameters requires large high-performance GPU clusters and long training periods lasting for months. Due to the inevitable hardware and software failures in large-scale clusters, maintaining uninterrupted and long-duration training is extremely challenging. As a result, A substantial amount of training time is devoted to task checkpoint saving and loading, task rescheduling and restart, and task manual anomaly checks, which greatly harms the overall training efficiency. To address these issues, we propose TRANSOM, a novel fault-tolerant LLM training system. In this work, we design three key subsystems: the training pipeline automatic fault tolerance and recovery mechanism named Transom Operator and Launcher (TOL), the training task multi-dimensional metric automatic anomaly detection system named Transom Eagle Eye (TEE), and the training checkpoint asynchronous access automatic fault tolerance and recovery technology named Transom Checkpoint Engine (TCE). Here, TOL manages the lifecycle of training tasks, while TEE is responsible for task monitoring and anomaly reporting. TEE detects training anomalies and reports them to TOL, who automatically enters the fault tolerance strategy to eliminate abnormal nodes and restart the training task. And the asynchronous checkpoint saving and loading functionality provided by TCE greatly shorten the fault tolerance overhead. The experimental results indicate that TRANSOM significantly enhances the efficiency of large-scale LLM training on clusters. Specifically, the pre-training time for GPT3-175B has been reduced by 28%, while checkpoint saving and loading performance have improved by a factor of 20.
Comment: 14 pages, 9 figures

الوصول الحر: http://arxiv.org/abs/2310.10046Test

المؤلفون: Sun, Yuqian, Wang, Hanyi, Chan, Pok Man, Tabibi, Morteza, Zhang, Yan, Lu, Huan, Chen, Yuheng, Lee, Chang Hee, Asadipour, Ali

مصطلحات موضوعية: Computer Science - Artificial Intelligence

الوصف: We address the integration of storytelling and Large Language Models (LLMs) to develop engaging and believable Social Chatbots (SCs) in community settings. Motivated by the potential of fictional characters to enhance social interactions, we introduce Storytelling Social Chatbots (SSCs) and the concept of story engineering to transform fictional game characters into "live" social entities within player communities. Our story engineering process includes three steps: (1) Character and story creation, defining the SC's personality and worldview, (2) Presenting Live Stories to the Community, allowing the SC to recount challenges and seek suggestions, and (3) Communication with community members, enabling interaction between the SC and users. We employed the LLM GPT-3 to drive our SSC prototypes, "David" and "Catherine," and evaluated their performance in an online gaming community, "DE (Alias)," on Discord. Our mixed-method analysis, based on questionnaires (N=15) and interviews (N=8) with community members, reveals that storytelling significantly enhances the engagement and believability of SCs in community settings.

الوصول الحر: http://arxiv.org/abs/2309.11478Test

المؤلفون: Chen, Yuheng, Cao, Pengfei, Chen, Yubo, Liu, Kang, Zhao, Jun

مصطلحات موضوعية: Computer Science - Computation and Language

الوصف: Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in multilingual PLMs, and introduces the Architecture-adapted Multilingual Integrated Gradients method, which successfully localizes knowledge neurons more precisely compared to current methods, and is more universal across various architectures and languages. Moreover, we conduct an in-depth exploration of knowledge neurons, leading to the following two important discoveries: (1) The discovery of Language-Independent Knowledge Neurons, which store factual knowledge in a form that transcends language. We design cross-lingual knowledge editing experiments, demonstrating that the PLMs can accomplish this task based on language-independent neurons; (2) The discovery of Degenerate Knowledge Neurons, a novel type of neuron showing that different knowledge neurons can store the same fact. Its property of functional overlap endows the PLMs with a robust mastery of factual knowledge. We design fact-checking experiments, proving that the degenerate knowledge neurons can help the PLMs to detect wrong facts. Experiments corroborate these findings, shedding light on the mechanisms of factual knowledge storage in multilingual PLMs, and contribute valuable insights to the field. The code is available at https://github.com/heng840/AMIGTest.
Comment: Accepted in the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)

الوصول الحر: http://arxiv.org/abs/2308.13198Test

المؤلفون: Yao, Wenjian, Bai, Jiajun, Liao, Wei, Chen, Yuheng, Liu, Mengjuan, Xie, Yao

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning

الوصف: Medical image segmentation is an important step in medical image analysis, especially as a crucial prerequisite for efficient disease diagnosis and treatment. The use of deep learning for image segmentation has become a prevalent trend. The widely adopted approach currently is U-Net and its variants. Additionally, with the remarkable success of pre-trained models in natural language processing tasks, transformer-based models like TransUNet have achieved desirable performance on multiple medical image segmentation datasets. In this paper, we conduct a survey of the most representative four medical image segmentation models in recent years. We theoretically analyze the characteristics of these models and quantitatively evaluate their performance on two benchmark datasets (i.e., Tuberculosis Chest X-rays and ovarian tumors). Finally, we discuss the main challenges and future trends in medical image segmentation. Our work can assist researchers in the related field to quickly establish medical segmentation models tailored to specific regions.
Comment: 18 pages, 8 figures

الوصول الحر: http://arxiv.org/abs/2308.05305Test

المؤلفون: Zhuang, Jialiang, Chen, Yuheng, Zhang, Yun, Zheng, Xiujuan

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

الوصف: Remote photoplethysmography (rPPG) is an attractive camera-based health monitoring method that can measure the heart rhythm from facial videos. Many well-established deep-learning models have been reported to measure heart rate (HR) and heart rate variability (HRV). However, most of these models usually require a 30-second facial video and enormous computational resources to obtain accurate and robust results, which significantly limits their applications in real-world scenarios. Hence, we propose a lightweight pulse extraction network, FastBVP-Net, to quickly measure heart rhythm via facial videos. The proposed FastBVP-Net uses a multi-frequency mode signal fusion (MMSF) mechanism to characterize the different modes of the raw signals in a decompose module and reconstruct the blood volume pulse (BVP) signal under a complex noise environment in a compose module. Meanwhile, an oversampling training scheme is used to solve the over-fitting problem caused by the limitations of the datasets. Then, the HR and HRV can be estimated based on the extracted BVP signals. Comprehensive experiments are conducted on the benchmark datasets to validate the proposed FastBVP-Net. For intra-dataset and cross-dataset testing, the proposed approach achieves better performance for HR and HRV estimation from 30-second facial videos with fewer computational burdens than the current well-established methods. Moreover, the proposed approach also achieves competitive results from 15-second facial videos. Therefore, the proposed FastBVP-Net has the potential to be applied in many real-world scenarios with shorter videos.
Comment: 9 pages, 2figures

الوصول الحر: http://arxiv.org/abs/2206.12558Test

المؤلفون: Gleicher, Michael, Yu, Xinyi, Chen, Yuheng

مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Human-Computer Interaction

الوصف: Classification methods for binary (yes/no) tasks often produce a continuously valued score. Machine learning practitioners must perform model selection, calibration, discretization, performance assessment, tuning, and fairness assessment. Such tasks involve examining classifier results, typically using summary statistics and manual examination of details. In this paper, we provide an interactive visualization approach to support such continuously-valued classifier examination tasks. Our approach addresses the three phases of these tasks: calibration, operating point selection, and examination. We enhance standard views and introduce task-specific views so that they can be integrated into a multi-view coordination (MVC) system. We build on an existing comparison-based approach, extending it to continuous classifiers by treating the continuous values as trinary (positive, unsure, negative) even if the classifier will not ultimately use the 3-way classification. We provide use cases that demonstrate how our approach enables machine learning practitioners to accomplish key tasks.
Comment: Author's version of journal paper accepted to appear

الوصول الحر: http://arxiv.org/abs/2204.08136Test

المؤلفون: Zhuang, Jialiang, Li, Bin, Zhang, Yun, Chen, Yuheng, Zheng, Xiujuan

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Human-Computer Interaction

الوصف: Blood pressure (BP) monitoring is vital in daily healthcare, especially for cardiovascular diseases. However, BP values are mainly acquired through the contact sensing method, which is inconvenient and unfriendly to continuous BP measurement. Hence, we propose an efficient end-to-end network to estimate the BP values from a facial video to achieve remote BP measurement in daily life. In this study, we first derived a Spatial-temporal map of a short-time (~15s) facial video. According to the Spatial-temporal map, we then regressed the BP ranges by a designed blood pressure classifier and simultaneously calculated the specific value by a blood pressure calculator in each BP range. In addition, we also developed an innovative oversampling training strategy to handle the unbalanced data distribution problem. Finally, we trained the proposed network on a private dataset ASPD and tested it on the popular dataset MMSE-HR. As a result, the proposed network achieved a state-of-the-art MAE of 12.35 mmHg and 9.5 mmHg on systolic and diastolic BP measurements, which is better than the recent works. It concludes that the proposed method has excellent potential for camera-based BP monitoring in real-world scenarios.
Comment: 7 pages, 7 figures

الوصول الحر: http://arxiv.org/abs/2203.03634Test