paper-with-me

Papers

GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures

2021-06-10 · Ivan Chelombiev, Daniel Justus, Douglas Orr, Anastasia Dietrich, Frithjof Gressmann, Alexandros Koliousis, Carlo Luschi

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and large parameter count. In this work we demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. First, we add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. Secondly, we rely on grouped transformations to reduce the computational cost of dense feed-forward layers and convolutions, while preserving the expressivity of the model. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales. We further highlight its improved efficiency, both in terms of floating-point operations (FLOPs) and time-to-train.

📄 PDF Abstract BibTeX arXiv:2106.05822

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
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…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

Enhanced Structured State Space Models via Grouped FIR Filtering and Attention Sink Mechanisms

2024-08-01 · Tian Meng, Yang Tao, Wuliang Yin

Structured State Space Models (SSMs) have emerged as compelling alternatives to Transformer architectures, offering linear-time complexity and superior performance in various sequence modeling tasks. Despite their advant…

MambaState Space Models

PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting

2025-08-19 · Tian Sun, Yuqi Chen, Weiwei Sun arxiv

Despite advances in the Transformer architecture, their effectiveness for long-term time series forecasting (LTSF) remains controversial. In this paper, we investigate the potential of integrating explicit periodicity mo…

Time Series Forecasting

GCA-ResUNet:Image segmentation in medical images using grouped coordinate attention

2025-11-18 · Jun Ding, Shang Gao arxiv

Medical image segmentation underpins computer-aided diagnosis and therapy by supporting clinical diagnosis, preoperative planning, and disease monitoring. While U-Net style convolutional neural networks perform well due …

Medical Image SegmentationComputational Efficiency

SMIXAE: Towards Unsupervised Manifold Discovery in Language Models

2026-05-09 · Collin Francel arxiv

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multid…

WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling

2025-08-21 · Jiacheng Li, Jianchao Tan, Zhidong Yang, Pingwei Sun 외 arxiv

Transformer architecture gradually dominates the LLM field. Recent advances in training optimization for Transformer-based large language models (LLMs) primarily focus on architectural modifications or optimizer adjustme…