Defining and Extracting generalizable interaction primitives from DNNs
Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI. To this end, Ren et al. (2024) have derived a series of theorems to prove that the inference score of a DNN can be explained as a small set of interactions between input variables. However, the lack of generalization power makes it still hard to consider such interactions as faithful primitive patterns encoded by the DNN. Therefore, given different DNNs trained for the same task, we develop a new method to extract interactions that are shared by these DNNs. Experiments show that the extracted interactions can better reflect common knowledge shared by different DNNs.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Technical Report: Quantifying and Analyzing the Generalization Power of a DNN
This paper proposes a new perspective for analyzing the generalization power of deep neural networks (DNNs), i.e., directly disentangling and analyzing the dynamics of generalizable and non-generalizable interaction enco…
A Linear Algebraic Approach to Model Parallelism in Deep Learning
Training deep neural networks (DNNs) in large-cluster computing environments is increasingly necessary, as networks grow in size and complexity. Local memory and processing limitations require robust data and model paral…
Deep LearningBiNoMaP: Learning Category-Level Bimanual Non-Prehensile Manipulation Primitives
Non-prehensile manipulation, encompassing ungraspable actions such as pushing, poking, pivoting, and wrapping, remains underexplored due to its contact-rich and analytically intractable nature. We revisit this problem fr…
Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN
In this paper, we find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power. We also discover that the confusing samples of a DNN, which are represented by non-g…
SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
Generalizable novel view synthesis aims to render unseen views from uncalibrated input images without requiring per-scene optimization. Recent feed-forward approaches based on 3D Gaussian Splatting have achieved promisin…
Novel View Synthesis