pith. sign in

arxiv: 2012.15701 · v2 · pith:ARICQWDRnew · submitted 2020-12-31 · 💻 cs.CL

BinaryBERT: Pushing the Limit of BERT Quantization

classification 💻 cs.CL
keywords binarybertternarybertmodelquantizationsplittingbinarycompression
0
0 comments X
read the original abstract

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks

    cs.LG 2026-06 unverdicted novelty 7.0

    StoMPP progressively binarizes BNN layers layerwise from input to output via stochastic masks, delivering depth-scalable accuracy gains in a fully STE-free regime by controlling activation-induced gradient blockades.

  2. LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

    cs.LG 2022-08 conditional novelty 7.0

    LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.

  3. SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

    cs.LG 2026-05 unverdicted novelty 6.0

    SURGE proposes a dual-path gradient compensator and adaptive scaler to learn better surrogate gradients for binary neural network training, outperforming prior methods on classification, detection, and language tasks.

  4. SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

    cs.LG 2026-05 unverdicted novelty 6.0

    SURGE introduces a dual-path gradient compensator and adaptive scaler to improve surrogate gradient estimation in binarized neural network training.

  5. SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

    cs.LG 2026-05 unverdicted novelty 6.0

    SURGE proposes a dual-path gradient compensator and adaptive gradient scaler to mitigate gradient mismatch in binary neural network training via auxiliary backpropagation.

  6. LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM

    cs.AR 2026-04 conditional novelty 6.0

    LOCALUT delivers 1.82x geometric mean speedup for quantized DNN inference on real UPMEM DRAM-PIM devices by using operation-packed LUTs with canonicalization, reordering, and slice streaming.