Banyan: Improved Representation Learning with Explicit Structure
원문 초록
We present Banyan, a model that efficiently learns semantic representations by leveraging explicit hierarchical structure. While transformers excel at scale, they struggle in low-resource settings. Conversely recent structured models have shown promise as efficient learners, but lack performance. Banyan bridges this gap with two key innovations: an entangled hierarchical tree structure and diagonalized message passing, enabling it to outperform larger transformer models with just 14 non-embedding parameters. It excels in low-resource settings, offering a viable alternative for under-represented languages and highlighting its potential for efficient, interpretable NLP in resource-constrained environments.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals' Mobility Beyond Visited Places
Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering
Multiple Object Stitching for Unsupervised Representation Learning
Similarity-Guided Diffusion for Contrastive Sequential Recommendation
When Graph Contrastive Learning Backfires: Spectral Vulnerability and Defense in Recommendation
ConViTac: Aligning Visual-Tactile Fusion with Contrastive Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.