How compositional generalization and creativity improve as diffusion models are trained
원문 초록
Natural data is often organized as a hierarchical composition of features. How many samples do generative models need in order to learn the composition rules, so as to produce a combinatorially large number of novel data? What signal in the data is exploited to learn those rules? We investigate these questions in the context of diffusion models both theoretically and empirically. Theoretically, we consider simple probabilistic context-free grammars - tree-like graphical models used to represent the hierarchical and compositional structure of data such as language and images. We demonstrate that diffusion models learn the grammar's composition rules with the sample complexity required for clustering features with statistically similar context, a process similar to the word2vec algorithm. However, this clustering emerges hierarchically: higher-level features associated with longer contexts require more data to be identified. This mechanism leads to a sample complexity that scales polynomially with the said context size. As a result, diffusion models trained on an intermediate dataset size generate data coherent up to a certain scale, but that lacks global coherence. We test these predictions in different domains, and find remarkable agreement: both generated texts and images achieve progressively larger coherence lengths as the training time or dataset size grows. We discuss connections between the hierarchical clustering mechanism we introduce here and the renormalization group in physics.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Tri-Learn Graph Fusion Network for Attributed Graph Clustering
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization
MiCo: Multiple Instance Learning with Context-Aware Clustering for Whole Slide Image Analysis
Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering
토론
이 논문과 연결된 포럼 글이 아직 없습니다.