paper-with-me

Papers

Layer-wise Representation Fusion for Compositional Generalization

2023-07-20 · Yafang Zheng, Lei Lin, Shuangtao Li, Yuxuan Yuan, Zhaohong Lai, Shan Liu, Biao Fu, Yidong Chen, Xiaodong Shi

Existing neural models are demonstrated to struggle with compositional generalization (CG), i.e., the ability to systematically generalize to unseen compositions of seen components. A key reason for failure on CG is that the syntactic and semantic representations of sequences in both the uppermost layer of the encoder and decoder are entangled. However, previous work concentrates on separating the learning of syntax and semantics instead of exploring the reasons behind the representation entanglement (RE) problem to solve it. We explain why it exists by analyzing the representation evolving mechanism from the bottom to the top of the Transformer layers. We find that the ``shallow'' residual connections within each layer fail to fuse previous layers' information effectively, leading to information forgetting between layers and further the RE problems. Inspired by this, we propose LRF, a novel \textbf{L}ayer-wise \textbf{R}epresentation \textbf{F}usion framework for CG, which learns to fuse previous layers' information back into the encoding and decoding process effectively through introducing a \emph{fuse-attention module} at each encoder and decoder layer. LRF achieves promising results on two realistic benchmarks, empirically demonstrating the effectiveness of our proposal.

📄 PDF Abstract BibTeX arXiv:2307.10799

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language

2022-10-02 · Zhenlin Xu, Marc Niethammer, Colin Raffel

Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various un…

DisentanglementRepresentation Learning

Rethinking Dense Linear Transformations: Stagewise Pairwise Mixing (SPM) for Near-Linear Training in Neural Networks

2025-12-30 · Peter Farag arxiv

Dense linear layers are a dominant source of computational and parametric cost in modern machine learning models, despite their quadratic complexity and often being misaligned with the compositional structure of learned …

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

2018-10-20 · NAACL 2019 6 · Mandar Joshi, Eunsol Choi, Omer Levy, Daniel S. Weld 외

Reasoning about implied relationships (e.g., paraphrastic, common sense, encyclopedic) between pairs of words is crucial for many cross-sentence inference problems. This paper proposes new methods for learning and using …

Common Sense ReasoningSentenceWord Embeddings

When does compositional structure yield compositional generalization? A kernel theory

2024-05-26 · Samuel Lippl, Kim Stachenfeld

Compositional generalization (the ability to respond correctly to novel combinations of familiar components) is thought to be a cornerstone of intelligent behavior. Compositionally structured (e.g. disentangled) represen…

MemorizationRepresentation Learning

CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation

2026-03-17 · Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan 외 arxiv

Generative models are increasingly used to augment medical imaging datasets for fairer AI, yet a key assumption often goes unexamined: that generators produce equally high-quality images across demographic groups. Models…

Medical Image Generation