Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness
Authors: 
Shide Du, Zihan Fang, Shiyang Lan, Yanchao Tan, Manuel Günther, Shiping Wang, Wenzhong GuoAuthors Info & Claims
Shide Du, Zihan Fang, Shiyang Lan, Yanchao Tan, Manuel Günther, Shiping Wang, Wenzhong GuoAuthors Info & ClaimsPages 8719 - 8729
Abstract
As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence multimedia technologies, it is imperative that we recognize the critical importance of trustworthiness in open-world, which has become ubiquitous in all aspects of daily life for everyone. However, several challenges may create a crisis of trust in current open-world artificial multimedia systems that need to be bridged: 1) Insufficient explanation of predictive results; 2) Inadequate generalization for learning models; 3) Poor adaptability to uncertain environments. Consequently, we explore a neural program to bridge trustworthiness and open-world learning, extending from single-modal to multi-modal scenarios for readers.1) To enhance design-level interpretability, we first customize trustworthy networks with specific physical meanings; 2) We then design environmental well-being task-interfaces via flexible learning regularizers for improving the generalization of trustworthy learning; 3) We propose to increase the robustness of trustworthy learning by integrating open-world recognition losses with agent mechanisms. Eventually, we enhance various trustworthy properties through the establishment of design-level explainability, environmental well-being task-interfaces and open-world recognition programs. As a result, these designed open-world protocols are applicable across a wide range of surroundings, under open-world multimedia recognition scenarios with significant performance improvements observed.
Supplementary Material
In this work, we explore a neural program to bridge trustworthiness and open-world learning, extending from single-modal to multi-modal scenarios for readers. 1) To enhance design-level interpretability, we first customize trustworthy networks with specific physical meanings; 2) We then design environmental well-being task-interfaces via flexible learning regularizers for improving the generalization of trustworthy learning; 3) We propose to increase the robustness of trustworthy learning by integrating open-world recognition losses with agent mechanisms. Eventually, we enhance various trustworthy properties through the establishment of design-level explainability, environmental well-being task-interfaces and open-world recognition programs. As a result, this work provides valuable insights for interested developers and accelerates research on the critical issues of trustworthiness, exploration and solution.
- Download
- 14.59 MB
References
[1]
Amir Beck and Marc Teboulle. 2009. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences, Vol. 2, 1 (2009), 183--202.
[2]
Deyu Bo, Xiao Wang, Chuan Shi, and Huawei Shen. 2021. Beyond low-frequency information in graph convolutional networks. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence. 3950--3957.
[3]
Terrance E. Boult, Przemyslaw A. Grabowicz, Derek S. Prijatelj, Roni Stern, Lawrence Holder, Joshua Alspector, Mohsen Jafarzadeh, Touqeer Ahmad, Akshay Raj Dhamija, Chunchun Li, Steve Cruz, Abhinav Shrivastava, Carl Vondrick, and Walter J. Scheirer. 2021. Towards a unifying framework for formal theories of novelty. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence. 15047--15052.
[4]
Benoît Colson, Patrice Marcotte, and Gilles Savard. 2007. An overview of bilevel optimization. Annals of Operations Research, Vol. 153 (2007), 235--256.
[5]
Zihan Fang, Shide Du, Xincan Lin, Jinbin Yang, Shiping Wang, and Yiqing Shi. 2023. DBO-Net: Differentiable bi-level optimization network for multi-view clustering. Information Sciences, Vol. 626 (2023), 572--585.
[6]
Nanyi Fei, Zhiwu Lu, Yizhao Gao, Guoxing Yang, Yuqi Huo, Jingyuan Wen, Haoyu Lu, Ruihua Song, Xin Gao, Tao Xiang, et al. 2022. Towards artificial general intelligence via a multimodal foundation model. Nature Communications, Vol. 13, 1 (2022), 3094.
[7]
Yifan Feng, Haoxuan You, Zizhao Zhang, Rongrong Ji, and Yue Gao. 2019. Hypergraph neural networks. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Vol. 33. 3558--3565.
[8]
Yue Gao, Yifan Feng, Shuyi Ji, and Rongrong Ji. 2023. HGNN+: General hypergraph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 3 (2023), 3181--3199.
[9]
Yu Geng, Zongbo Han, Changqing Zhang, and Qinghua Hu. 2021. Uncertainty-aware multi-view representation learning. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence. 7545--7553.
[10]
Kim Huat Goh, Le Wang, Adrian Yong Kwang Yeow, Hermione Poh, Ke Li, Joannas Jie Lin Yeow, and Gamaliel Yu Heng Tan. 2021. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nature Communications, Vol. 12, 1 (2021), 711.
[11]
Karol Gregor and Yann LeCun. 2010. Learning fast approximations of sparse coding. In Proceedings of the Twenty-Seventh International Conference on Machine Learning. 399--406.
[12]
Ning Gui, Danni Ge, and Ziyin Hu. 2019. AFS: An attention-based mechanism for supervised feature selection. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. 3705--3713.
[13]
Zongbo Han, Changqing Zhang, Huazhu Fu, and Joey Tianyi Zhou. 2023. Trusted multi-view classification with dynamic evidential fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 2 (2023), 2551--2566.
[14]
Davinder Kaur, Suleyman Uslu, Kaley J Rittichier, and Arjan Durresi. 2022. Trustworthy artificial intelligence: A review. ACM Computing Surveys, Vol. 55, 2 (2022), 1--38.
[15]
Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the Fifth International Conference on Learning Representations. 1--14.
[16]
Johannes Klicpera, Aleksandar Bojchevski, and Stephan Günnemann. [n.d.]. Predict then propagate: Graph neural networks meet personalized pagerank. In Proceedings of the Seventh International Conference on Learning Representations. 1--15.
[17]
Bo Li, Peng Qi, Bo Liu, Shuai Di, Jingen Liu, Jiquan Pei, Jinfeng Yi, and Bowen Zhou. 2023 a. Trustworthy AI: From principles to practices. ACM Computing Surveys, Vol. 55, 9 (2023), 1--46.
[18]
Haoyang Li, Xin Wang, Ziwei Zhang, and Wenwu Zhu. 2022b. OOD-GNN: Out-of-distribution generalized graph neural network. IEEE Transactions on Knowledge and Data Engineering (2022).
[19]
Mingjie Li, Yisen Wang, Xingyu Xie, and Zhouchen Lin. 2022a. Optimization inspired multi-branch equilibrium models. In Proceedings of the Tenth International Conference on Learning Representations. 1--32.
[20]
Xingfeng Li, Zhenwen Ren, Quansen Sun, and Zhi Xu. 2023 b. Auto-weighted tensor schatten p-Norm for robust multi-view graph clustering. Pattern Recognition, Vol. 134 (2023), 109083.
[21]
Guangcan Liu, Zhouchen Lin, and Yong Yu. 2010. Robust subspace segmentation by low-rank representation. In Proceedings of the Twenty-Seventh International Conference on Machine Learning. 663--670.
[22]
Juncheng Liu, Bryan Hooi, Kenji Kawaguchi, and Xiaokui Xiao. 2022. MGNNI: Multiscale graph neural networks with implicit layers. In Advances in Neural Information Processing Systems. 21358--21370.
[23]
Juncheng Liu, Kenji Kawaguchi, Bryan Hooi, Yiwei Wang, and Xiaokui Xiao. 2021. EIGNN: Efficient infinite-depth graph neural networks. In Advances in Neural Information Processing Systems. 18762--18773.
[24]
Ghada Sokar, Zahra Atashgahi, Mykola Pechenizkiy, and Decebal Constantin Mocanu. 2022. Where to pay attention in sparse training for feature selection? Advances in Neural Information Processing Systems, 1627--1642.
[25]
Yiwei Sun, Suhang Wang, Xianfeng Tang, Tsung-Yu Hsieh, and Vasant G. Honavar. 2020. Adversarial attacks on graph neural networks via node injections: A hierarchical reinforcement learning approach. In Proceedings of the Twenty-Ninth International World Wide Web Conference. 673--683.
[26]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.
[27]
Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the Sixth International Conference on Learning Representations. 1--12.
[28]
Ricardo Vinuesa, Hossein Azizpour, Iolanda Leite, Madeline Balaam, Virginia Dignum, Sami Domisch, Anna Felländer, Simone Daniela Langhans, Max Tegmark, and Francesco Fuso Nerini. 2020. The role of artificial intelligence in achieving the sustainable development goals. Nature Communications, Vol. 11, 1 (2020), 233.
[29]
Xinhang Wan, Jiyuan Liu, Weixuan Liang, Xinwang Liu, Yi Wen, and En Zhu. 2022. Continual multi-view clustering. In Proceedings of the Thirtieth ACM International Conference on Multimedia. 3676--3684.
[30]
Chang-Dong Wang, Man-Sheng Chen, Ling Huang, Jian-Huang Lai, and S Yu Philip. 2020a. Smoothness regularized multiview subspace clustering with kernel learning. IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, 11 (2020), 5047--5060.
[31]
Min Wang, Hao Yang, and Qing Cheng. 2022c. GCL: Graph calibration loss for trustworthy graph neural network. In Proceedings of the Thirtieth ACM International Conference on Multimedia. 988--996.
[32]
Shiping Wang, Zhaoliang Chen, Shide Du, and Zhouchen Lin. 2022a. Learning deep sparse regularizers with applications to multi-view clustering and semi-supervised classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2022), 5042--5055.
[33]
Shiping Wang, Zhihao Wu, Yuhong Chen, and Yong Chen. 2023. Beyond graph convolutional network: An interpretable regularizer-centered optimization framework. In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence. 1--15.
[34]
Tao Wang, Di Jin, Rui Wang, Dongxiao He, and Yuxiao Huang. 2022b. Powerful graph convolutional networks with adaptive propagation mechanism for homophily and heterophily. In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence. 4210--4218.
[35]
Xiao Wang, Meiqi Zhu, Deyu Bo, Peng Cui, Chuan Shi, and Jian Pei. 2020b. AM-GCN: Adaptive multi-channel graph convolutional networks. In Proceedings of the Twenty-Sixth ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1243--1253.
[36]
Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In Proceedings of the Thirty-Sixth International Conference on Machine Learning. 6861--6871.
[37]
Man Wu, Shirui Pan, and Xingquan Zhu. 2020. OpenWGL: Open-world graph learning. In Proceedings of the Twentieth IEEE International Conference on Data Mining. 681--690.
[38]
Xingyu Xie, Qiuhao Wang, Zenan Ling, Xia Li, Guangcan Liu, and Zhouchen Lin. 2023. Optimization induced equilibrium networks: An explicit optimization perspective for understanding equilibrium models. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 3 (2023), 3604--3616.
[39]
Yuan Xie, Wensheng Zhang, Yanyun Qu, Longquan Dai, and Dacheng Tao. 2018. Hyper-Laplacian regularized multilinear multiview self-representations for clustering and semisupervised learning. IEEE Transactions on Cybernetics, Vol. 50, 2 (2018), 572--586.
[40]
Pengyang Yu, Chaofan Fu, Yanwei Yu, Chao Huang, Zhongying Zhao, and Junyu Dong. 2022. Multiplex heterogeneous graph convolutional network. In Proceedings of the Twenty-Eighth ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2377--2387.
[41]
Changqing Zhang, Huazhu Fu, Qinghua Hu, Xiaochun Cao, Yuan Xie, Dacheng Tao, and Dong Xu. 2020. Generalized latent multi-view subspace clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, 1 (2020), 86--99.
[42]
Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, and Cheekong Lee. 2022. Protgnn: Towards self-explaining graph neural networks. In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence. 9127--9135.
[43]
Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, and Chen Change Loy. 2023. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 4 (2023), 4396--4415.
[44]
Meiqi Zhu, Xiao Wang, Chuan Shi, Houye Ji, and Peng Cui. 2021. Interpreting and unifying graph neural networks with an optimization framework. In Proceedings of the Thirtieth International World Wide Web Conference. 1215--1226.
[45]
Liansheng Zhuang, Haoyuan Gao, Zhouchen Lin, Yi Ma, Xin Zhang, and Nenghai Yu. 2012. Non-negative low rank and sparse graph for semi-supervised learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2328--2335.
Index Terms
- Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness
Recommendations
Trustworthy Machine Learning: Robustness, Generalization, and Interpretability
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningMachine learning is becoming increasingly important in today's world. Beyond its powerful performances, there has been an emerging concern about the trustworthiness of machine learning, including but not limited to: robustness to malicious attacks, ...
An Open-World Novelty Generator for Authoring Reinforcement Learning Environment of Standardized Toolkits
Multi-disciplinary Trends in Artificial IntelligenceAbstractCurrent research in Reinforcement Learning (RL) is based on closed-world learning environment where the environment remains fixed and unchanged throughout the agent’s training and application session. The fixed environment may be prone to failure ...
Open-World Social Event Classification
WWW '23: Proceedings of the ACM Web Conference 2023With the rapid development of Internet and the expanding scale of social media, social event classification has attracted increasing attention. The key to social event classification is effectively leveraging the visual and textual semantics for ...
Comments
Information & Contributors
Information
Published In
October 2023
9913 pages
ISBN:9798400701085
DOI:10.1145/3581783
- General Chairs:
- Abdulmotaleb El Saddik,
- Tao Mei,
- Rita Cucchiara,
- Program Chairs:
- Marco Bertini,
- Diana Patricia Tobon Vallejo,
- Pradeep K. Atrey,
- M. Shamim Hossain
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 27 October 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Key Research and Development Plan of China
- National Natural Science Foundation of China
Conference
MM '23
Sponsor:
MM '23: The 31st ACM International Conference on Multimedia
October 29 - November 3, 2023
Ottawa ON, Canada
Acceptance Rates
Overall Acceptance Rate 995 of 4,171 submissions, 24%
Upcoming Conference
MM '24
- Sponsor:
- sigmm
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 116Total Downloads
- Downloads (Last 12 months)116
- Downloads (Last 6 weeks)4
Reflects downloads up to 18 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in