Lune

CVPR2021Top-tier venue

Learning Decision Trees Recurrently Through Communication

Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata

Abstract

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. ViT-NeT: Interpretable Vision Transformers with Neural Tree DecoderSangwon Kim, Jae-Yeal Nam, ByoungChul KoICML 2022 · 97 citations

Builds on3

  1. Discovering Symbolic Models from Deep Learning with Inductive BiasesMiles D. Cranmer, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, Rui Xu et al.NeurIPS 2020 · 736 citations
  2. Explaining Neural Networks Semantically and QuantitativelyRunjin Chen, Hao Chen, Ge Huang, Jie Ren et al.ICCV 2019 · 60 citations
  3. Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language LearningAngeliki Lazaridou, Anna Potapenko, Olivier TielemanACL 2020 · 11 citations

Related papers

  1. From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature SelectionMoritz Vandenhirtz, Julia E. VogtICML 2025
  2. Learning Accurate and Interpretable Decision Rule Sets from Neural NetworksLitao Qiao, Weijia Wang, Bill LinAAAI 2021 · 53 citations
  3. Learn from A Rationalist: Distilling Intermediate Interpretable RationalesJiayi Dai, Randy GoebelICML 2026
  4. Learning to Select Prototypical Parts for Interpretable Sequential Data ModelingYifei Zhang, Neng Gao, Cunqing MaAAAI 2023 · 10 citations
  5. Model Interpretability and Rationale Extraction by Input Mask OptimizationMarc Felix Brinner, Sina ZarrießACL Findings 2023 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines