检索结果-内蒙古大学图书馆

Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Kai Zhang, Kun Liu, Qi Huang, Zhenya Zhang, Mengdi Wu, Wei Cheng, Mingyue Chen, Enhong Anhui Province Key Lab. of Big Data Analysis and Application University of S&T of China State Key Laboratory of Cognitive Intelligence Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Meituan Beijing China Anhui Province Key Lab. of Big Data Analysis and Application University of S&T of China Hefei China

Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlab.led target domain. Existing studies in this task attach more attention to the sequence modeling of sentences while largely ignoring the rich domain-invariant semantics embedded in graph structures (i.e., the part-of-speech tags and dependency relations). As an important aspect of exploring characteristics of language comprehension, adaptive graph representations have played an essential role in recent years. To this end, in the paper, we aim to explore the possibility of learning invariant semantic features from graph-like structures in CDSC. Specifically, we present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs. More specifically, we first raise a POS-Transformer module to extract sequential semantic features from the word sequences as well as the part-of-speech tags. Then, we design a Hybrid Graph Attention (HGAT) module to generate syntax-based semantic features by considering the transferable dependency relations. Finally, we devise an Integrated aDaptive Strategy (IDS) to guide the joint learning process of both modules. Extensive experiments on four public datasets indicate that GAST achieves comparable effectiveness to a range of state-of-the-art models. © 2022, CC BY.

关键词： Sentiment analysis

Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net

学校读者我要写书评

暂无评论

Semantic-Preserving Abstractive Text Summarization with Siam...

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Jiang, Deqiang Ren, Bo School of Computer Science and Technology University of Science and Technology of China. China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China IFLYTEK Co. Ltd. China Tencent Youtu Lab China

ISBN: (纸本)9781955917766

We propose a novel siamese generative adversarial net for abstractive text summarization (SSPGAN), which can preserve the main semantics of the source text. Different from previous generative adversarial net based methods, SSPGAN is equipped with a siamese semanticpreserving discriminator, which can not only be trained to discriminate the machine-generated summaries from the human-summarized ones, but also ensure the semantic consistency between the source text and target summary. As a consequence of the min-max game between the generator and the siamese semantic-preserving discriminator, the generator can generate a summary that conveys the key content of the source text more accurately. Extensive experiments on several text summarization benchmarks in different languages demonstrate the effectiveness of the proposed method. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Semantics

Full-atom protein pocket design via iterative refinement 23

学校读者我要写书评

暂无评论

Full-atom protein pocket design via iterative refinement

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zaixi Zhang Zepu Lu Zhongkai Hao Marinka Zitnik Qi Liu Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China and Harvard University Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua-Bosch Joint ML Center Tsinghua Harvard University

The design and optimization of functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10% in AAR and RMSD metrics.

关键词：

Backdoor Defense via Deconfounded Representation Learning

学校读者我要写书评

暂无评论

Backdoor Defense via Deconfounded Representation Learning

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zaixi Zhang Qi Liu Zhicai Wang Zepu Lu Qingyong Hu Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei Anhui China University of Science and Technology of China Hong Kong University of Science and Technology

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been made to detect and remove backdoors from backdoored DNNs, it is still not clear whether a backdoor-free clean model can be directly obtained from poisoned datasets. In this paper, we first construct a causal graph to model the generation process of poisoned data and find that the backdoor attack acts as the confounder, which brings spurious associations between the input images and target lab.ls, making the model predictions less reliable. Inspired by the causal understanding, we propose the Causality-inspired Backdoor Defense (CBD), to learn deconfounded representations for reliable classification. Specifically, a backdoored model is intentionally trained to capture the confounding effects. The other clean model dedicates to capturing the desired causal effects by minimizing the mutual information with the confounding representations from the backdoored model and employing a sample-wise re-weighting scheme. Extensive experiments on multiple benchmark datasets against 6 state-of-the-art attacks verify that our proposed defense method is effective in reducing backdoor threats while maintaining high accuracy in predicting benign samples. Further analysis shows that CBD can also resist potential adaptive attacks. The code is availab.e at https://***/zaixizhang/CBD.

关键词：

Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jiquan Guo, Junliang Zhu, Yongxin Sheng, Xin Jiang, Deqiang Ren, Bo Xu, Linli Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology China Tencent YouTu Lab China

The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years. While one of the key principles of GEC is to keep the correct parts unchanged and avoid over-correction, previous sequence-to-sequence (seq2seq) models generate results from scratch, which are not guaranteed to follow the original sentence structure and may suffer from the over-correction problem. In the meantime, the recently proposed sequence tagging models can overcome the over-correction problem by only generating edit operations, but are conditioned on human designed language-specific tagging lab.ls. In this paper, we combine the pros and alleviate the cons of both models by proposing a novel Sequence-to-Action (S2A) module. The S2A module jointly takes the source and target sentences as input, and is able to automatically generate a token-level action sequence before predicting each token, where each action is generated from three choices named SKIP, COPY and GENerate. Then the actions are fused with the basic seq2seq framework to provide final predictions. We conduct experiments on the benchmark datasets of both English and Chinese GEC tasks. Our model consistently outperforms the seq2seq baselines, while being able to significantly alleviate the over-correction problem as well as holding better generality and diversity in the generation results compared to the sequence tagging models. © 2022, CC BY.

关键词： Error correction

Deep Geometry Handling and Fragment-wise Molecular 3D Graph Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Odin Huang, Yufei Cheng, Shichen Yu, Mengyao Zhang, Xujun Lin, Haitao Zeng, Yundian Wang, Mingyang Wu, Zhenxing Zhao, Huifeng Zhang, Zaixi Hua, Chenqing Kang, Yu Cui, Sunliang Pan, Peichen Hsieh, Chang-Yu Hou, Tingjun College of Pharmaceutical Sciences Zhejiang University Zhejiang Hangzhou310058 China Zhejiang University Zhejiang Hangzhou310058 China Anhui Province Key Lab of Big Data Analysis and Application University of Science and Technology of China Anhui Hefei China Montreal Institute for Learning Algorithms McGill University MontrealQC Canada

3D structure-based molecular graph generation has attracted tremendous attention for its vast potential in designing potent drug candidates. Most earlier approaches follow an atom-wise paradigm, incrementally adding atoms to a partially built molecular fragment within protein pockets. These methods, while effective in designing tightly bound ligands, often overlook other essential properties such as synthesizability and drugability. The fragment-wise generation paradigm offers a promising solution by assembling chemically sensible fragments to reduce synthesis difficulty. However, a common challenge across both atom-wise and fragment-wise methods lies in their limited ability to co-design plausible chemical and geometrical structures, resulting in distorted conformations and inferior binding tendencies. In response to this challenge, we introduce the Deep Geometry Handling protocol, a more abstract design that decomposes the entire geometry into multiple sets of geometric variables, extending the design focus beyond the model architecture. Through a comprehensive review of existing geometry-related models, we identify and discuss six protocols, each with its own strengths and weaknesses. Building upon these insights, we propose a novel hybrid strategy, culminating in the development of FragGen - the first geometry-reliable, fragment-wise molecular generation method. FragGen marks a significant leap forward in the quality of generated geometry and the synthesis accessibility of molecules-addressing two major challenges in the application of molecular generation algorithms. The efficacy of FragGen is further validated by its successful application in designing type II kinase inhibitors at the nanomolar level, grounding its algorithmic advancements in real-world drug development. We believe that this concept-algorithm-application loop will not only inspire researchers working on other geometry-centric tasks to look beyond architecture design, but also offer a concrete

关键词： Geometry

Estimation Soil Organic Matter Using Airborne Hyperspectral Imagery 13

学校读者我要写书评

暂无评论

Estimation Soil Organic Matter Using Airborne Hyperspectral ...

13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2023

作者： Chen, Lihan Tan, Kun Wang, Xue Pan, Chen China University of Mining and Technology Key Laboratory for Land Environment and Disaster Monitoring of Nasg Xuzhou221116 China Shanghai200241 China East China Normal University Key Lab. of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities Ministry of Natural Resources Shanghai200241 China East China Normal University School of Geographic Sciences Shanghai200241 China Shanghai Municipal Institute of Surveying and Mapping Shanghai200063 China

ISBN: (纸本)9798350395570

Soil organic matter (SOM) content plays an important part in soil environmental quality definition and should be estimated necessarily. The conventional methods for the SOM concentration assessment are mainly based on lab.ratory physicochemical analysis, which is costly and time consuming. Visible and near-infrared (Vis-NIR) spectroscopy offers the potential to quantify the SOM over large areas based on the soil spectral characteristics. Therefore, an innovative methodology using visible and near-infrared reflectance spectra are proposed in this work to monitoring the SOM rapidly and economically. A total of 91 soil samples and their spectral data collected in Yitong of China were utilized to characterize the relationship between the soil reflectance spectrum and SOM. First, continuum removal (CR) and competitive adaptive reweighted sampling (CARS) are introduced as the pretreatment method and wavebands selection method respectively, which can amplify the weak spectral characteristic. After the preprocessing phases, Partial Least Squares (PLS), Random Forest (RF) and XGBoost are carried out to estimate the SOM and the results show that XGBoost yields the best performance with R2 of 0.9968 on training set and 0.6831 on testing set. Finally, the distribution trend of SOM in the whole study area is mapped using the optimal CR-CARS-XGBoost model. © 2023 IEEE.

关键词： Soils

APGL4SR: A Generic Framework with Adaptive and Personalized Global Collab.rative Information in Sequential Recommendation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yin, Mingjia Wang, Hao Xu, Xiang Wu, Likang Zhao, Sirui Guo, Wei Liu, Yong Tang, Ruiming Lian, Defu Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Huawei Singapore Research Center Singapore Huawei Noah's Ark Lab Shenzhen China

The sequential recommendation system has been widely studied for its promising effectiveness in capturing dynamic preferences buried in users' sequential behaviors. Despite the considerable achievements, existing methods usually focus on intra-sequence modeling while overlooking exploiting global collab.rative information by inter-sequence modeling, resulting in inferior recommendation performance. Therefore, previous works attempt to tackle this problem with a global collab.rative item graph constructed by pre-defined rules. However, these methods neglect two crucial properties when capturing global collab.rative information, i.e., adaptiveness and personalization, yielding sub-optimal user representations. To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collab.rative information into sequential recommendation systems. Specifically, we first learn an adaptive global graph among all items and capture global collab.rative information with it in a self-supervised fashion, whose computational burden can be further alleviated by the proposed SVD-based accelerator. Furthermore, based on the graph, we propose to extract and utilize personalized item correlations in the form of relative positional encoding, which is a highly compatible manner of personalizing the utilization of global collab.rative information. Finally, the entire framework is optimized in a multi-task learning paradigm, thus each part of APGL4SR can be mutually reinforced. As a generic framework, APGL4SR can not only outperform other baselines with significant margins, but also exhibit promising versatility, the ability to learn a meaningful global collab.rative graph, and the ability to alleviate the dimensional collapse issue of item embeddings. The code is availab.e at https://***/Graph-Team/APGL4SR. © 2023, CC BY.

关键词： Recommender systems

Backdoor Defense via Deconfounded Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zaixi Liu, Qi Wang, Zhicai Lu, Zepu Hu, Qingyong Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong University of Science and Technology of China China

关键词： Deep neural networks