Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
134 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness (2308.03666v4)

Published 7 Aug 2023 in stat.ML and cs.LG

Abstract: As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence 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 artificial intelligence 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. These designed open-world protocols are applicable across a wide range of surroundings, under open-world multimedia recognition scenarios with significant performance improvements observed.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Carlo Abrate and Francesco Bonchi. 2021. Counterfactual graphs for explainable classification of brain networks. In Proceedings of the Twenty-Seventh ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2495–2504.
  2. Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion 58 (2020), 82–115.
  3. Amir Beck and Marc Teboulle. 2009. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences 2, 1 (2009), 183–202.
  4. Beyond low-frequency information in graph convolutional networks. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence. 3950–3957.
  5. Towards a unifying framework for formal theories of novelty. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence. 15047–15052.
  6. An overview of bilevel optimization. Annals of Operations Research 153 (2007), 235–256.
  7. DBO-Net: Differentiable bi-level optimization network for multi-view clustering. Information Sciences 626 (2023), 572–585.
  8. Towards artificial general intelligence via a multimodal foundation model. Nature Communications 13, 1 (2022), 3094.
  9. Hypergraph neural networks. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Vol. 33. 3558–3565.
  10. HGNN++{}^{\mbox{+}}start_FLOATSUPERSCRIPT + end_FLOATSUPERSCRIPT: General hypergraph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2023), 3181–3199.
  11. Uncertainty-aware multi-view representation learning. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence. 7545–7553.
  12. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nature Communications 12, 1 (2021), 711.
  13. 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.
  14. AFS: An attention-based mechanism for supervised feature selection. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. 3705–3713.
  15. Trusted multi-view classification with dynamic evidential fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 2 (2023), 2551–2566.
  16. Trustworthy artificial intelligence: A review. ACM Computing Surveys 55, 2 (2022), 1–38.
  17. 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.
  18. Predict then propagate: Graph neural networks meet personalized pagerank. In Proceedings of the Seventh International Conference on Learning Representations. 1–15.
  19. Trustworthy AI: From principles to practices. ACM Computing Surveys 55, 9 (2023), 1–46.
  20. OOD-GNN: Out-of-distribution generalized graph neural network. IEEE Transactions on Knowledge and Data Engineering (2022). Doi: 10.1109/TKDE.2022.3193725.
  21. Optimization inspired multi-branch equilibrium models. In Proceedings of the Tenth International Conference on Learning Representations. 1–32.
  22. OrphicX: A causality-inspired latent variable model for interpreting graph neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 13719–13728.
  23. Robust subspace segmentation by low-rank representation. In Proceedings of the Twenty-Seventh International Conference on Machine Learning. 663–670.
  24. Trustworthy AI: A computational perspective. ACM Transactions on Intelligent Systems and Technology 14, 1 (2022), 1–59.
  25. MGNNI: Multiscale graph neural networks with implicit layers. In Advances in Neural Information Processing Systems. 21358–21370.
  26. EIGNN: Efficient infinite-depth graph neural networks. In Advances in Neural Information Processing Systems. 18762–18773.
  27. Anchors: High-precision model-agnostic explanations. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. 1527–1535.
  28. Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions. Nature Communications 10, 1 (2019), 5024.
  29. Where to pay attention in sparse training for feature selection? Advances in Neural Information Processing Systems, 1627–1642.
  30. 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.
  31. Attention is all you need. In Advances in Neural Information Processing Systems. 5998–6008.
  32. Graph attention networks. In Proceedings of the Sixth International Conference on Learning Representations. 1–12.
  33. The role of artificial intelligence in achieving the sustainable development goals. Nature Communications 11, 1 (2020), 233.
  34. Continual multi-view clustering. In Proceedings of the Thirtieth ACM International Conference on Multimedia. 3676–3684.
  35. Smoothness regularized multiview subspace clustering with kernel learning. IEEE Transactions on Neural Networks and Learning Systems 32, 11 (2020), 5047–5060.
  36. GCL: Graph calibration loss for trustworthy graph neural network. In Proceedings of the Thirtieth ACM International Conference on Multimedia. 988–996.
  37. Learning deep sparse regularizers with applications to multi-view clustering and semi-supervised classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2022), 5042–5055.
  38. Beyond graph convolutional network: An interpretable regularizer-centered optimization framework. In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence. 1–15.
  39. 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.
  40. 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.
  41. Simplifying graph convolutional networks. In Proceedings of the Thirty-Sixth International Conference on Machine Learning. 6861–6871.
  42. OpenWGL: Open-world graph learning. In Proceedings of the Twentieth IEEE International Conference on Data Mining. 681–690.
  43. Optimization induced equilibrium networks: An explicit optimization perspective for understanding equilibrium models. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2023), 3604–3616.
  44. Hyper-Laplacian regularized multilinear multiview self-representations for clustering and semisupervised learning. IEEE Transactions on Cybernetics 50, 2 (2018), 572–586.
  45. Multiplex heterogeneous graph convolutional network. In Proceedings of the Twenty-Eighth ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2377–2387.
  46. Generalized latent multi-view subspace clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence 42, 1 (2020), 86–99.
  47. Protgnn: Towards self-explaining graph neural networks. In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence. 9127–9135.
  48. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2023), 4396–4415.
  49. Interpreting and unifying graph neural networks with an optimization framework. In Proceedings of the Thirtieth International World Wide Web Conference. 1215–1226.
  50. 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.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now