paper-with-me

홈 › Papers

Defining and Quantifying the Emergence of Sparse Concepts in DNNs

2021-11-11 · CVPR 2023 1 · Jie Ren, Mingjie Li, Qirui Chen, Huiqi Deng, Quanshi Zhang

This paper aims to illustrate the concept-emerging phenomenon in a trained DNN. Specifically, we find that the inference score of a DNN can be disentangled into the effects of a few interactive concepts. These concepts can be understood as causal patterns in a sparse, symbolic causal graph, which explains the DNN. The faithfulness of using such a causal graph to explain the DNN is theoretically guaranteed, because we prove that the causal graph can well mimic the DNN's outputs on an exponential number of different masked samples. Besides, such a causal graph can be further simplified and re-written as an And-Or graph (AOG), without losing much explanation accuracy.

📄 PDF Abstract BibTeX arXiv:2111.06206

Code (1)

sjtu-xai-lab/aog 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs

2023-04-26 · Mingjie Li, Quanshi Zhang

In this technical note, we aim to explain a deep neural network (DNN) by quantifying the encoded interactions between input variables, which reflects the DNN's inference logic. Specifically, we first rethink the definiti…

Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models

2023-05-03 · Qihan Ren, Jiayang Gao, Wen Shen, Quanshi Zhang

This study aims to prove the emergence of symbolic concepts (or more precisely, sparse primitive inference patterns) in well-trained deep neural networks (DNNs). Specifically, we prove the following three conditions for …

Emergence of Concepts in DNNs?

2022-11-11 · Tim Räz

The present paper reviews and discusses work from computer science that proposes to identify concepts in internal representations (hidden layers) of DNNs. It is examined, first, how existing methods actually identify con…

Philosophy

Neural (Tangent Kernel) Collapse

2023-05-25 · NeurIPS 2023 11

This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) phenomenon, which refers to the emergen…

Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

2023-04-03 · Wen Shen, Lei Cheng, Yuxiao Yang, Mingjie Li 외

In this paper, we explain the inference logic of large language models (LLMs) as a set of symbolic concepts. Many recent studies have discovered that traditional DNNs usually encode sparse symbolic concepts. However, bec…

Sentence