{"title":"See How You Read? Multi-Reading Habits Fusion Reasoning for Multi-Modal Fake News Detection","authors":"Lianwei Wu, Pusheng Liu, Yanning Zhang","doi":"10.1609/aaai.v37i11.26609","DOIUrl":"https://doi.org/10.1609/aaai.v37i11.26609","url":null,"abstract":"The existing approaches based on different neural networks automatically capture and fuse the multimodal semantics of news, which have achieved great success for fake news detection. However, they still suffer from the limitations of both shallow fusion of multimodal features and less attention to the inconsistency between different modalities. To overcome them, we propose multi-reading habits fusion reasoning networks (MRHFR) for multi-modal fake news detection. In MRHFR, inspired by people's different reading habits for multimodal news, we summarize three basic cognitive reading habits and put forward cognition-aware fusion layer to learn the dependencies between multimodal features of news, so as to deepen their semantic-level integration. To explore the inconsistency of different modalities of news, we develop coherence constraint reasoning layer from two perspectives, which first measures the semantic consistency between the comments and different modal features of the news, and then probes the semantic deviation caused by unimodal features to the multimodal news content through constraint strategy. Experiments on two public datasets not only demonstrate that MRHFR not only achieves the excellent performance but also provides a new paradigm for capturing inconsistencies between multi-modal news.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"10 1","pages":"13736-13744"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89942549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"FeedFormer: Revisiting Transformer Decoder for Efficient Semantic Segmentation","authors":"J. Shim, Hyunwoo Yu, Kyeongbo Kong, Suk-Ju Kang","doi":"10.1609/aaai.v37i2.25321","DOIUrl":"https://doi.org/10.1609/aaai.v37i2.25321","url":null,"abstract":"With the success of Vision Transformer (ViT) in image classification, its variants have yielded great success in many downstream vision tasks. Among those, the semantic segmentation task has also benefited greatly from the advance of ViT variants. However, most studies of the transformer for semantic segmentation only focus on designing efficient transformer encoders, rarely giving attention to designing the decoder. Several studies make attempts in using the transformer decoder as the segmentation decoder with class-wise learnable query. Instead, we aim to directly use the encoder features as the queries. This paper proposes the Feature Enhancing Decoder transFormer (FeedFormer) that enhances structural information using the transformer decoder. Our goal is to decode the high-level encoder features using the lowest-level encoder feature. We do this by formulating high-level features as queries, and the lowest-level feature as the key and value. This enhances the high-level features by collecting the structural information from the lowest-level feature. Additionally, we use a simple reformation trick of pushing the encoder blocks to take the place of the existing self-attention module of the decoder to improve efficiency. We show the superiority of our decoder with various light-weight transformer-based decoders on popular semantic segmentation datasets. Despite the minute computation, our model has achieved state-of-the-art performance in the performance computation trade-off. Our model FeedFormer-B0 surpasses SegFormer-B0 with 1.8% higher mIoU and 7.1% less computation on ADE20K, and 1.7% higher mIoU and 14.4% less computation on Cityscapes, respectively. Code will be released at: https://github.com/jhshim1995/FeedFormer.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"5 1","pages":"2263-2271"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90036945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Generative Label Enhancement with Gaussian Mixture and Partial Ranking","authors":"Yunan Lu, Liang He, Fan Min, Weiwei Li, Xiuyi Jia","doi":"10.1609/aaai.v37i7.26078","DOIUrl":"https://doi.org/10.1609/aaai.v37i7.26078","url":null,"abstract":"Label distribution learning (LDL) is an effective learning paradigm for dealing with label ambiguity. When applying LDL, the datasets annotated with label distributions (i.e., the real-valued vectors like the probability distribution) are typically required. Unfortunately, most existing datasets only contain the logical labels, and manual annotating with label distributions is costly. To address this problem, we treat the label distribution as a latent vector and infer its posterior by variational Bayes. Specifically, we propose a generative label enhancement model to encode the process of generating feature vectors and logical label vectors from label distributions in a principled way. In terms of features, we assume that the feature vector is generated by a Gaussian mixture dominated by the label distribution, which captures the one-to-many relationship from the label distribution to the feature vector and thus reduces the feature generation error. In terms of logical labels, we design a probability distribution to generate the logical label vector from a label distribution, which captures partial label ranking in the logical label vector and thus provides a more accurate guidance for inferring the label distribution. Besides, to approximate the posterior of the label distribution, we design a inference model, and derive the variational learning objective. Finally, extensive experiments on real-world datasets validate our proposal.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"10 1","pages":"8975-8983"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91193205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Blending Advertising with Organic Content in E-commerce via Virtual Bids","authors":"Carlos Carrion, Zenan Wang, Harikesh S. Nair, Xianghong Luo, Yulin Lei, Peiqin Gu, Xiliang Lin, Wenlong Chen, Junsheng Jin, Fanan Zhu, Changping Peng, Yongjun Bao, Zhangang Lin, Weipeng P. Yan, Jingping Shao","doi":"10.1609/aaai.v37i13.26835","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26835","url":null,"abstract":"It has become increasingly common that sponsored content (i.e., paid ads) and non-sponsored content are jointly displayed to users, especially on e-commerce platforms. Thus, both of these contents may interact together to influence their engagement behaviors. In general, sponsored content helps brands achieve their marketing goals and provides ad revenue to the platforms. In contrast, non-sponsored content contributes to the long-term health of the platform through increasing users' engagement. A key conundrum to platforms is learning how to blend both of these contents allowing their interactions to be considered and balancing these business objectives. This paper proposes a system built for this purpose and applied to product detail pages of JD.COM, an e-commerce company. This system achieves three objectives: (a) Optimization of competing business objectives via Virtual Bids allowing the expressiveness of the valuation of the platform for these objectives. (b) Modeling the users' click behaviors considering explicitly the influence exerted by the sponsored and non-sponsored content displayed alongside through a deep learning approach. (c) Consideration of a Vickrey-Clarke-Groves (VCG) Auction design compatible with the allocation of ads and its induced externalities. Experiments are presented demonstrating the performance of the proposed system. Moreover, our approach is fully deployed and serves all traffic through JD.COM's mobile application.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"12 1","pages":"15476-15484"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91200659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Liyuan Gao, Huixin Zhan, Austin Chen, Victor S. Sheng
{"title":"Towards Fair and Selectively Privacy-Preserving Models Using Negative Multi-Task Learning (Student Abstract)","authors":"Liyuan Gao, Huixin Zhan, Austin Chen, Victor S. Sheng","doi":"10.1609/aaai.v37i13.26967","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26967","url":null,"abstract":"Deep learning models have shown great performances in natural language processing tasks. While much attention has been paid to improvements in utility, privacy leakage and social bias are two major concerns arising in trained models. In order to tackle these problems, we protect individuals' sensitive information and mitigate gender bias simultaneously. First, we propose a selective privacy-preserving method that only obscures individuals' sensitive information. Then we propose a negative multi-task learning framework to mitigate the gender bias which contains a main task and a gender prediction task. We analyze two existing word embeddings and evaluate them on sentiment analysis and a medical text classification task. Our experimental results show that our negative multi-task learning framework can mitigate the gender bias while keeping models’ utility.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"21 2 1","pages":"16214-16215"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89545466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Low Resource Quantitative Information Extraction via Structure Searching and Prefix-Based Text Generation","authors":"Tongliang Li, Zixiang Wang, Zhoujun Li","doi":"10.1609/aaai.v37i11.26540","DOIUrl":"https://doi.org/10.1609/aaai.v37i11.26540","url":null,"abstract":"Quantitative information plays an important part in the financial and data analysis areas. Prior work relied on pattern-matching methods and complex hand-crafted rules to extract quantitative information due to the lack of labeled data. Such methods can be unstable and difficult to scale to the open domain. In this paper, we study quantitative information extraction in the low-resource setting. We propose a search-based approach by searching from the syntactic structures to acquire basic training data. The search process is simple yet effective. Then, a prefix-based text-to-text generation method is employed to extract the quantitative information. The prefix design can fully leverage pre-trained language models for text generation to serve the information extraction purpose. Experimental results show that our approaches achieves high performance with a limited amount of labeled data. The extraction result could further boost the performance of other tasks such as quantitative reasoning.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"6 1","pages":"13112-13120"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90300230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"TC-DWA: Text Clustering with Dual Word-Level Augmentation","authors":"Bo Cheng, Ximing Li, Yi Chang","doi":"10.1609/aaai.v37i6.25868","DOIUrl":"https://doi.org/10.1609/aaai.v37i6.25868","url":null,"abstract":"The pre-trained language models, e.g., ELMo and BERT, have recently achieved promising performance improvement in a wide range of NLP tasks, because they can output strong contextualized embedded features of words. Inspired by their great success, in this paper we target at fine-tuning them to effectively handle the text clustering task, i.e., a classic and fundamental challenge in machine learning. Accordingly, we propose a novel BERT-based method, namely Text Clustering with Dual Word-level Augmentation (TCDWA). To be specific, we formulate a self-training objective and enhance it with a dual word-level augmentation technique. First, we suppose that each text contains several most informative words, called anchor words, supporting the full text semantics. We use the embedded features of anchor words as augmented data, which are selected by ranking the norm-based attention weights of words. Second, we formulate an expectation form of word augmentation, which is equivalent to generating infinite augmented features, and further suggest a tractable approximation of Taylor expansion for efficient optimization. To evaluate the effectiveness of TCDWA, we conduct extensive experiments on several benchmark text datasets. The results demonstrate that TCDWA consistently outperforms the state-of-the-art baseline methods. Code available: https://github.com/BoCheng-96/TC-DWA.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"66 1","pages":"7113-7121"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90370895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Actionness Inconsistency-Guided Contrastive Learning for Weakly-Supervised Temporal Action Localization","authors":"Zhilin Li, Zilei Wang, Qinying Liu","doi":"10.1609/aaai.v37i2.25237","DOIUrl":"https://doi.org/10.1609/aaai.v37i2.25237","url":null,"abstract":"Weakly-supervised temporal action localization (WTAL) aims to detect action instances given only video-level labels. To address the challenge, recent methods commonly employ a two-branch framework, consisting of a class-aware branch and a class-agnostic branch. In principle, the two branches are supposed to produce the same actionness activation. However, we observe that there are actually many inconsistent activation regions. These inconsistent regions usually contain some challenging segments whose semantic information (action or background) is ambiguous. In this work, we propose a novel Actionness Inconsistency-guided Contrastive Learning (AICL) method which utilizes the consistent segments to boost the representation learning of the inconsistent segments. Specifically, we first define the consistent and inconsistent segments by comparing the predictions of two branches and then construct positive and negative pairs between consistent segments and inconsistent segments for contrastive learning. In addition, to avoid the trivial case where there is no consistent sample, we introduce an action consistency constraint to control the difference between the two branches. We conduct extensive experiments on THUMOS14, ActivityNet v1.2, and ActivityNet v1.3 datasets, and the results show the effectiveness of AICL with state-of-the-art performance. Our code is available at https://github.com/lizhilin-ustc/AAAI2023-AICL.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"40 1","pages":"1513-1521"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87203855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Martijn Oldenhof, Gergely Ács, Balázs Pejó, Ansgar Schuffenhauer, Nicholas Holway, Noé Sturm, Arne Dieckmann, Oliver Fortmeier, Eric Boniface, Clément Mayer, Arnaud Gohier, Peter Schmidtke, Ritsuya Niwayama, Dieter Kopecky, Lewis Mervin, Prakash Chandra Rathi, Lukas Friedrich, András Formanek, Peter Antal, Jordon Rahaman, Adam Zalewski, Wouter Heyndrickx, Ezron Oluoch, Manuel Stößel, Michal Vančo, David Endico, Fabien Gelus, Thaïs De Boisfossé, Adrien Darbier, Ashley Nicollet, Matthieu Blottière, Maria Telenczuk, Van Tien Nguyen, Thibaud Martinez, Camille Boillet, Kelvin Moutet, Alexandre Picosson, Aurélien Gasser, Inal Djafar, Antoine Simon, Ádám Arany, Jaak Simm, Yves Moreau, Ola Engkvist, Hugo Ceulemans, Camille Marini, Mathieu Galtier
{"title":"Industry-Scale Orchestrated Federated Learning for Drug Discovery","authors":"Martijn Oldenhof, Gergely Ács, Balázs Pejó, Ansgar Schuffenhauer, Nicholas Holway, Noé Sturm, Arne Dieckmann, Oliver Fortmeier, Eric Boniface, Clément Mayer, Arnaud Gohier, Peter Schmidtke, Ritsuya Niwayama, Dieter Kopecky, Lewis Mervin, Prakash Chandra Rathi, Lukas Friedrich, András Formanek, Peter Antal, Jordon Rahaman, Adam Zalewski, Wouter Heyndrickx, Ezron Oluoch, Manuel Stößel, Michal Vančo, David Endico, Fabien Gelus, Thaïs De Boisfossé, Adrien Darbier, Ashley Nicollet, Matthieu Blottière, Maria Telenczuk, Van Tien Nguyen, Thibaud Martinez, Camille Boillet, Kelvin Moutet, Alexandre Picosson, Aurélien Gasser, Inal Djafar, Antoine Simon, Ádám Arany, Jaak Simm, Yves Moreau, Ola Engkvist, Hugo Ceulemans, Camille Marini, Mathieu Galtier","doi":"10.1609/aaai.v37i13.26847","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26847","url":null,"abstract":"To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLODDY (grant n°831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLODDY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLODDY platform generated new scientific discoveries which are described in a companion paper.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135504264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Longwei Guo, Hao Zhu, Yuanxun Lu, Menghua Wu, Xun Cao
{"title":"RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs","authors":"Longwei Guo, Hao Zhu, Yuanxun Lu, Menghua Wu, Xun Cao","doi":"10.1609/aaai.v37i1.25149","DOIUrl":"https://doi.org/10.1609/aaai.v37i1.25149","url":null,"abstract":"We propose a robust and accurate non-parametric method for single-view 3D face reconstruction (SVFR). While tremendous efforts have been devoted to parametric SVFR, a visible gap still lies between the result 3D shape and the ground truth. We believe there are two major obstacles: 1) the representation of the parametric model is limited to a certain face database; 2) 2D images and 3D shapes in the fitted datasets are distinctly misaligned. To resolve these issues, a large-scale pseudo 2D&3D dataset is created by first rendering the detailed 3D faces, then swapping the face in the wild images with the rendered face. These pseudo 2D&3D pairs are created from publicly available datasets which eliminate the gaps between 2D and 3D data while covering diverse appearances, poses, scenes, and illumination. We further propose a non-parametric scheme to learn a well-generalized SVFR model from the created dataset, and the proposed hierarchical signed distance function turns out to be effective in predicting middle-scale and small-scale 3D facial geometry. Our model outperforms previous methods on FaceScape-wild/lab and MICC benchmarks and is well generalized to various appearances, poses, expressions, and in-the-wild environments. The code is released at https://github.com/zhuhao-nju/rafare.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135504304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
