paper-with-me

홈 › Papers

Kformer: Knowledge Injection in Transformer Feed-Forward Layers

2022-01-15 · Yunzhi Yao, Shaohan Huang, Li Dong, Furu Wei, Huajun Chen, Ningyu Zhang

Recent days have witnessed a diverse set of knowledge injection models for pre-trained language models (PTMs); however, most previous studies neglect the PTMs' own ability with quantities of implicit knowledge stored in parameters. A recent study has observed knowledge neurons in the Feed Forward Network (FFN), which are responsible for expressing factual knowledge. In this work, we propose a simple model, Kformer, which takes advantage of the knowledge stored in PTMs and external knowledge via knowledge injection in Transformer FFN layers. Empirically results on two knowledge-intensive tasks, commonsense reasoning (i.e., SocialIQA) and medical question answering (i.e., MedQA-USMLE), demonstrate that Kformer can yield better performance than other knowledge injection technologies such as concatenation or attention-based injection. We think the proposed simple model and empirical findings may be helpful for the community to develop more powerful knowledge injection methods. Code available in https://github.com/zjunlp/Kformer.

📄 PDF Abstract BibTeX arXiv:2201.05742

Code (1)

zjunlp/Kformer 공식 구현 pytorch

Tasks

Language ModellingMedical Question AnsweringMedQAQuestion Answering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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…
Position-Wise Feed-Forward Layer 설명 없음
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…
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 $x$…

Similar Papers 제목 키워드 기반

LKFormer: Large Kernel Transformer for Infrared Image Super-Resolution

2024-01-22 · Feiwei Qin, Kang Yan, Changmiao Wang, Ruiquan Ge 외

Given the broad application of infrared technology across diverse fields, there is an increasing emphasis on investigating super-resolution techniques for infrared images within the realm of deep learning. Despite the im…

Image Super-ResolutionInfrared image super-resolutionSuper-Resolution

RankFormer: Listwise Learning-to-Rank Using Listwide Labels

2023-06-09 · Maarten Buyl, Paul Missault, Pierre-Antoine Sondag

Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is typically assumed to reflect a re…

Knowledge DistillationLearning-To-Rank

Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket

2024-01-04 · Zhaokun Zhou, Kaiwei Che, Wei Fang, Keyu Tian 외

Spiking Neural Networks (SNNs), known for their biologically plausible architecture, face the challenge of limited performance. The self-attention mechanism, which is the cornerstone of the high-performance Transformer a…

image-classificationImage ClassificationSelf-Supervised Learning

QKFormer: Hierarchical Spiking Transformer using Q-K Attention

2024-03-25 · Chenlin Zhou, Han Zhang, Zhaokun Zhou, Liutao Yu 외

Spiking Transformers, which integrate Spiking Neural Networks (SNNs) with Transformer architectures, have attracted significant attention due to their potential for energy efficiency and high performance. However, existi…

InEKFormer: A Hybrid State Estimator for Humanoid Robots

2025-11-20 · Lasse Hohmeyer, Mihaela Popescu, Ivan Bergonzani, Dennis Mronga 외 arxiv

Humanoid robots have great potential for a wide range of applications, including industrial and domestic use, healthcare, and search and rescue missions. However, bipedal locomotion in different environments is still a c…