Learning Decision Trees Recurrently Through Communication
Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata
摘要
Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn iterative binary sub-decisions, inducing sparsity and transparency in the decision making process. The key aspect of our model is its ability to build a decision tree whose structure is encoded into the memory representation of a Recurrent Neural Network jointly learned by two models communicating through message passing. In addition, our model assigns a semantic meaning to each decision in the form of binary attributes, providing concise, semantic and relevant rationalizations to the user. On three benchmark image classification datasets, including the large-scale ImageNet, our model generates human interpretable binary decision sequences explaining the predictions of the network while maintaining state-of-the-art accuracy.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 1 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
引用它的顶会 Paper1
它引用的 Paper3
- Discovering Symbolic Models from Deep Learning with Inductive BiasesMiles D. Cranmer, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, Rui Xu 等NeurIPS 2020 · 736 次引用
- Explaining Neural Networks Semantically and QuantitativelyRunjin Chen, Hao Chen, Ge Huang, Jie Ren 等ICCV 2019 · 60 次引用
- Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language LearningAngeliki Lazaridou, Anna Potapenko, Olivier TielemanACL 2020 · 11 次引用
相关 Paper
- From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature SelectionMoritz Vandenhirtz, Julia E. VogtICML 2025
- Learning Accurate and Interpretable Decision Rule Sets from Neural NetworksLitao Qiao, Weijia Wang, Bill LinAAAI 2021 · 53 次引用
- Learn from A Rationalist: Distilling Intermediate Interpretable RationalesJiayi Dai, Randy GoebelICML 2026
- Learning to Select Prototypical Parts for Interpretable Sequential Data ModelingYifei Zhang, Neng Gao, Cunqing MaAAAI 2023 · 10 次引用
- Model Interpretability and Rationale Extraction by Input Mask OptimizationMarc Felix Brinner, Sina ZarrießACL Findings 2023 · 2 次引用
