检索结果-内蒙古大学图书馆

EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Yingjie Si, Jiasheng Zhao, Yibo Zhu, Haiyang Zhou, Deyu He, Yulan School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute United Kingdom

Automatic multi-hop fact verification task has gained significant attention in recent years. Despite impressive results, these well-designed models perform poorly on out-of-domain data. One possible solution is to augment the training data with counterfactuals, which are generated by minimally altering the causal features of the original data. However, current counterfactual data augmentation techniques fail to handle multi-hop fact verification due to their incapability to preserve the complex logical relationships within multiple correlated texts. In this paper, we overcome this limitation by developing a rationale-sensitive method to generate linguistically diverse and label-flipping counterfactuals while preserving logical relationships. In specific, the diverse and fluent counterfactuals are generated via an Explain-Edit-Generate architecture. Moreover, the checking and filtering modules are proposed to regularize the counterfactual data with logical relations and flipped labels. Experimental results show that the proposed approach outperforms the SOTA baselines and can generate linguistically diverse counterfactual data without disrupting their logical relationships1 Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Multi-Signal Fusion of Social Diffusion Graph with Bi-Directional Semantic Consistency

学校读者我要写书评

暂无评论

Multi-Signal Fusion of Social Diffusion Graph with Bi-Direct...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Huacheng Li Chunhe Xia Tianbo Wang Wanshuang Lin Changnan Jiang Chen Chen Yuan Zhao Key Laboratory of Beijing Network Technology Beihang University Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing Guangxi Normal University School of Cyber Science and Technology Beihang University Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai

Devising diffusion graph to learn user representations is a crucial step in studying information propagation prediction. However, previous works mainly focused on structural and temporal features. To better incorporate content features, we introduce the Backward Decomposition and Forward Preservation mechanisms. The former involves decomposing content features for initializing node signals in the diffusion graph, thus fusing user features with content features. The latter aims to maintain node features generated by graph encoder consistent with the original content features. A series of experiments demonstrate that our model outperforms state-of-the-art models, and both mechanisms significantly enhance the prediction performance. Furthermore, our methods enables the features generated by the diffusion graph to more effectively incorporate features from various semantic spaces, whether encoded by language models or generated by graph embedding algorithms.

关键词：

Deep Video Cascade Clustering from Video Structures

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wang, Zihua Zhu, Hongyuan Mi, Siya Zhang, Yu Geng, Xin School of Computer Science and Engineering The Key Lab of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China A*STAR Singapore School of Cyber Science and Engineering Southeast University Nanjing211189 China Purple Mountain Laboratories Nanjing211189 China

Video clustering is a critical unsupervised learning task where, unlike in supervised video classification, category labels are not *** main challenge lies in learning an effective video representation without annotations to group similar *** this paper, we introduce a novel unsupervised video learning paradigm called Deep Video Cascade Clustering ($\text{DVC}^2$).Unlike existing image-based clustering methods, $\text{DVC}^2$ first learns an initial video representation through frame clustering, which serves as guidance. Subsequently, the video clustering results are aligned with both the long-term and short-term video structures and their nearest *** conduct a comprehensive evaluation of $\text{DVC}^2$ on benchmark video datasets, including UCF101 and Kinetic-400, and achieve state-of-the-art video clustering results. Additionally, we evaluate the performance of combining self-supervised learning with K-means *** findings validate the effectiveness of $\text{DVC}^2$ in unsupervised video clustering scenarios. © 2024, The Authors. All rights reserved.

关键词： Unsupervised learning

Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tang, Wei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Weakly supervised machine learning algorithms are able to learn from ambiguous samples or labels, e.g., multi-instance learning or partial-label learning. However, in some real-world tasks, each training sample is associated with not only multiple instances but also a candidate label set that contains one ground-truth label and some false positive labels. Specifically, at least one instance pertains to the ground-truth label while no instance belongs to the false positive labels. In this paper, we formalize such problems as multi-instance partial-label learning (MIPL). Existing multi-instance learning algorithms and partial-label learning algorithms are suboptimal for solving MIPL problems since the former fail to disambiguate a candidate label set, and the latter cannot handle a multi-instance bag. To address these issues, a tailored algorithm named MIPLGP, i.e., Multi-Instance Partial-Label learning with Gaussian Processes, is proposed. MIPLGP first assigns each instance with a candidate label set in an augmented label space, then transforms the candidate label set into a logarithmic space to yield the disambiguated and continuous labels via an exclusive disambiguation strategy, and last induces a model based on the Gaussian processes. Experimental results on various datasets validate that MIPLGP is superior to well-established multi-instance learning and partial-label learning algorithms for solving MIPL problems. Our code and datasets will be made publicly available. Copyright © 2022, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

A Higher-Order Semantic Dependency Parser

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Bin Fan, Yunlong Sataer, Yikemaiti Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Higher-order features bring significant accuracy gains in semantic dependency parsing. However, modeling higher-order features with exact inference is NP-hard. Graph neural networks (GNNs) have been demonstrated to be an effective tool for solving NP-hard problems with approximate inference in many graph learning tasks. Inspired by the success of GNNs, we investigate building a higher-order semantic dependency parser by applying GNNs. Instead of explicitly extracting higher-order features from intermediate parsing graphs, GNNs aggregate higher-order information concisely by stacking multiple GNN layers. Experimental results show that our model outperforms the previous state-of-the-art parser on the SemEval 2015 Task 18 English datasets. © 2022, CC BY-NC-SA.

关键词： Graph neural networks

Towards Few-Shot Learning in the Open World: A Review and Beyond

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xue, Hui An, Yuexuan Qin, Yongchun Li, Wenqian Wu, Yixin Che, Yongjuan Fang, Pengfei Zhang, Min-Ling The School of Computer Science and Engineering Southeast University Nanjing210096 China The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing211189 China The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

Human intelligence is characterized by our ability to absorb and apply knowledge from the world around us, especially in rapidly acquiring new concepts from minimal examples, underpinned by prior knowledge. Few-shot learning (FSL) aims to mimic this capacity by enabling significant generalizations and transferability. However, traditional FSL frameworks often rely on assumptions of clean, complete, and static data, conditions that are seldom met in real-world environments. Such assumptions falter in the inherently uncertain, incomplete, and dynamic contexts of the open world. This paper presents a comprehensive review of recent advancements designed to adapt FSL for use in open-world settings. We categorize existing methods into three distinct types of open-world few-shot learning: those involving varying instances, varying classes, and varying distributions. Each category is discussed in terms of its specific challenges and methods, as well as its strengths and weaknesses. We standardize experimental settings and metric benchmarks across scenarios, and provide a comparative analysis of the performance of various methods. In conclusion, we outline potential future research directions for this evolving field. It is our hope that this review will catalyze further development of effective solutions to these complex challenges, thereby advancing the field of artificial intelligence. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

RoKEPG: RoBERTa and Knowledge Enhancement for Prescription Generation of Traditional Chinese Medicine

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pu, Hua Mi, Jiacong Lu, Shan He, Jieyue School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University Jiangsu Nanjing210018 China Nanjing Fenghuo Tiandi Communication Technology Co. Ltd Jiangsu Nanjing211161 China

Traditional Chinese medicine (TCM) prescription is the most critical form of TCM treatment, and uncovering the complex nonlinear relationship between symptoms and TCM is of great significance for clinical practice and assisting physicians in diagnosis and treatment. Although there have been some studies on TCM prescription generation, these studies consider a single factor and directly model the symptom-prescription generation problem mainly based on symptom descriptions, lacking guidance from TCM knowledge. To this end, we propose a RoBERTa and Knowledge Enhancement model for Prescription Generation of Traditional Chinese Medicine (RoKEPG). RoKEPG is firstly pre-trained by our constructed TCM corpus, followed by fine-tuning the pre-trained model, and the model is guided to generate TCM prescriptions by introducing four classes of knowledge of TCM through the attention mask matrix. Experimental results on the publicly available TCM prescription dataset show that RoKEPG improves the F1 metric by about 2% over the baseline model with the best results. © 2023, CC BY.

关键词： Diagnosis

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang-Xin, Shi Tong, Wei Zhi, Zhou Jie-Jing, Shao Xin-Yan, Han Yu-Feng, Li National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Computer Science and Engineering Southeast University China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified. In this paper, we disclose that heavy fine-tuning may even lead to non-negligible performance deterioration on tail classes, and lightweight fine-tuning is more effective. The reason is attributed to inconsistent class conditions caused by heavy fine-tuning. With the observation above, we develop a low-complexity and accurate long-tail learning algorithms LIFT with the goal of facilitating fast prediction and compact models by adaptive lightweight fine-tuning. Experiments clearly verify that both the training time and the learned parameters are significantly reduced with more accurate predictive performance compared with state-of-the-art approaches. The implementation code is available at https://***/shijxcs/LIFT. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

A Constructive Method Based on Dynamic Solution Space for Travelling Salesman Problem

学校读者我要写书评

暂无评论

A Constructive Method Based on Dynamic Solution Space for Tr...

International Conference on Advanced Cloud and Big Data (CBD)

作者： Xiaoxin Bai LuLi LuLi Hanqian Wu School of Computer Science and Engineering Southeast University China School of Cyber Science and Engineering Southeast University China Suzhou Centennail College China Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University China

Neural combinatorial optimization (NCO) has emerged as a promising field to solve the combinatorial optimization problem (COP) as automatically learning the solvers less relying on domain-specific expert knowledge. Constructive Method (ConsM) is the most widely used approach in NCO for solving various COPs and their variations. However, few literature elucidates the underlying principles of ConsM, hindering further optimization. In this paper, we analyze the efficiency principle of ConsM for COPs from the perspective of discrete solution space and summarize its design principles. These principles can serve as guidelines for designing novel constructive policy. Based on these principles, we reviewed the existing ConsM models and identified that the design of existing decoder introduced certain noises, which negatively impacted the policy performance. Therefore, we designed a novel decoder in line with the aforementioned principles. Notably, our method can be applied to all ConsM models and yielded significant improvements compared to the original. We evaluated our method on Traveling Salesman Problem(TSP) and the experimental results verified the effectiveness and efficiency of our method, supporting our analysis of ConsM. In particular, we reduced the average optimality gap from 1.16% to 0.62% for TSP100 compared to Sym-NCOs, keeping the hyperparameters constant.

关键词：