mlsanityData to 14 Oct 2026

Effective Quantization Methods for Recurrent Neural Networks

arXiv 1611.10176 ↗First posted 30 Nov 2016cs.LG cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Reducing bit-widths of weights, activations, and gradients of a Neural Network can shrink its storage size and memory usage, and also allow for faster training and inference by exploiting bitwise operations. However, previous attempts for quantization of RNNs show considerable performance degradation when using low bit-width weights and activations. In this paper, we propose methods to quantize the structure of gates and interlinks in LSTM and GRU cells. In addition, we propose balanced quantization methods for weights to further reduce performance degradation. Experiments on PTB and IMDB datasets confirm effectiveness of our methods as performances of our models match or surpass the previous state-of-the-art of quantized RNN.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 2; 2023: 2; 2024: 1; 2025: 4; 2026: 1.

14 papers.

Sort:

By area:

  1. 2021A Survey on Green Deep Learningcited by 52
  2. 2021BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantizationcited by 39
  3. 2024CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimizationcited by 15
  4. 20214-bit Quantization of LSTM-based Speech Recognition Modelscited by 8
  5. 2023NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Modelscited by 7
  6. 2022Training Integer-Only Deep Recurrent Neural Networkscited by 5
  7. 2025Histogram-Equalized Quantization for logic-gated Residual Neural Networkscited by 4
  8. 2021iRNN: Integer-only Recurrent Neural Networkcited by 3
  9. 2022Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inferencecited by 2
  10. 2026Quantizing Recursive Reasoning Modelscited by 2
  11. 2023AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networkscited by 0
  12. 2025HadamRNN: Binary and Sparse Ternary Orthogonal RNNscited by 0
2 more
  1. 2025Dynamic Clustering for Personalized Federated Learning on Heterogeneous Edge Devicescited by 0
  2. 2025Downsized and Compromised?: Assessing the Faithfulness of Model Compressioncited by 0