paper-with-me

Papers

ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation

2024-11-22 · Junzhang Liu, Tingkai Liu, Yueyuan Sui, Stephen Xia

We introduce ElastiFormer, a post-training technique that adapts pretrained Transformer models into an elastic counterpart with variable inference time compute. ElastiFormer introduces small routing modules (as low as .00006% additional trainable parameters) to dynamically selects subsets of network parameters and input tokens to be processed by each layer of the pretrained network in an inputdependent manner. The routing modules are trained using self-distillation losses to minimize the differences between the output of the pretrained-model and their elastic counterparts. As ElastiFormer makes no assumption regarding the modality of the pretrained Transformer model, it can be readily applied to all modalities covering causal language modeling, image modeling as well as visual-language modeling tasks. We show that 20% to 50% compute saving could be achieved for different components of the transformer layer, which could be further reduced by adding very low rank LoRA weights (rank 1) trained via the same distillation objective. Finally, by comparing routing trained on different subsets of ImageNet, we show that ElastiFormer is robust against the training domain.

📄 PDF Abstract BibTeX arXiv:2411.15281

Code (0)

등록된 구현이 없습니다.

Tasks

Causal Language ModelingLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

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…
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…
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…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

RedMotion: Motion Prediction via Redundancy Reduction

2023-06-19 · Royden Wagner, Omer Sahin Tas, Marvin Klemp, Carlos Fernandez 외

We introduce RedMotion, a transformer model for motion prediction in self-driving vehicles that learns environment representations via redundancy reduction. Our first type of redundancy reduction is induced by an interna…

Decodermotion predictionPredictionRepresentation Learning+3

IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers

2021-06-23 · NeurIPS 2021 12 · Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang 외

The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffe…

Efficient ViTs

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

2023-09-07 · Yusuf Brima, Ulf Krumnack, Simone Pika, Gunther Heidemann

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can captur…

Keyword SpottingSelf-Supervised LearningSpeaker Identification

Beyond Pairwise Correlations: Higher-Order Redundancies in Self-Supervised Representation Learning

2024-12-02 · David Zollikofer, Béni Egressy, Frederik Benzing, Matthias Otth 외

Several self-supervised learning (SSL) approaches have shown that redundancy reduction in the feature embedding space is an effective tool for representation learning. However, these methods consider a narrow notion of r…

Representation LearningSelf-Supervised Learning

Adaptive Learned Image Compression with Graph Neural Networks

2026-03-26 · Yunuo Chen, Bing He, Zezheng Lyu, Hongwei Hu 외 arxiv

Efficient image compression relies on modeling both local and global redundancy. Most state-of-the-art (SOTA) learned image compression (LIC) methods are based on CNNs or Transformers, which are inherently rigid. Standar…

Image Compression