Always Keep Your Promises: DynamicLRP, A Model-Agnostic Solution To Layer-Wise Relevance Propagation
By: Kevin Lee, Pablo Millan Arias
Potential Business Impact:
Explains AI decisions for any computer program.
Layer-wise Relevance Propagation (LRP) provides principled attribution for neural networks through conservation properties and foundations in Deep Taylor Decomposition. However, existing implementations operate at the module level, requiring architecture-specific propagation rules and modifications. These limit the generality of target model and sustainability of implementations as architectures evolve. We introduce DynamicLRP, a model-agnostic LRP framework operating at the tensor operation level. By decomposing attribution to individual operations within computation graphs and introducing a novel mechanism for deferred activation resolution, named the Promise System, our approach achieves true architecture agnosticity while maintaining LRP's theoretical guarantees. This design operates independently of backpropagation machinery, enabling operation on arbitrary computation graphs without model modification and side-by-side execution with gradient backpropagation. Being based on computation graphs, this method is theoretically extensible to other deep learning libraries that support auto-differentiation. We demonstrate faithfulness matching or exceeding specialized implementations (1.77 vs 1.69 ABPC on VGG, equivalent performance on ViT, 93.70\% and 95.06\% top-1 attribution accuracy for explaining RoBERTa-large and Flan-T5-large answers on SQuADv2, respectively) while maintaining practical efficiency on models with hundreds of millions of parameters. We achieved 99.92\% node coverage across 31,465 computation graph nodes from 15 diverse architectures, including state-space models (Mamba), audio transformers (Whisper), and multimodal systems (DePlot) without any model-specific code with rules for 47 fundamental operations implemented. Our operation-level decomposition and Promise System establish a sustainable, extensible foundation for LRP across evolving architectures.
Similar Papers
When LRP Diverges from Leave-One-Out in Transformers
Machine Learning (CS)
Makes AI understand itself better.
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs
Machine Learning (CS)
Makes AI smarter and smaller, removing bad parts.
Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
Machine Learning (CS)
Shows why AI makes certain decisions.