Neural Network Compression

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 77 papers with code (193 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• NeRV: Neural Representations for Videos
  26 Oct 2021 3 repositories listed Syntology ran 7 of 10 samples · 3 unverified · 10 pointer-only (licence)
  In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H.
• ZeroQ: A Novel Zero Shot Quantization Framework
  1 Jan 2020 3 repositories listed Syntology ran 4 of 19 samples · 15 unverified
  Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0.
• Learning Filter Basis for Convolutional Neural Network Compression
  23 Aug 2019 3 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images.
• Data-Free Learning of Student Networks
  2 Apr 2019 3 repositories listed
  Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors.
• MUSCO: Multi-Stage Compression of neural networks
  24 Mar 2019 3 repositories listed
  The low-rank tensor approximation is very promising for the compression of deep neural networks.
• Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
  28 Jan 2019 3 repositories listed Syntology ran 1 of 6 samples · 5 unverified
  The majority of existing literature focuses on training quantized DNNs, while this work examines the less-studied topic of quantizing a floating-point model without (re)training.
• Soft Weight-Sharing for Neural Network Compression
  13 Feb 2017 3 repositories listed
  The success of deep learning in numerous application domains created the de- sire to run and train them on mobile devices.
• spred: Solving L₁ Penalty with SGD
  3 Oct 2022 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  We propose to minimize a generic differentiable objective with L₁ constraint using a simple reparametrization and straightforward stochastic gradient descent.
• Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
  1 Feb 2022 2 repositories listed Syntology ran 0 of 17 samples · 17 unverified
  Every modern neural network model has quite a few pointwise nonlinearities in its architecture, and such operation induces additional memory costs which -- as we show -- can be significantly reduced by quantization of…
• Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems
  20 Nov 2020 2 repositories listed
  In this paper, we propose to modify the structure and training process of DNN models for complex image classification tasks to achieve in-network compression in the early network layers.
• Teacher-Class Network: A Neural Network Compression Mechanism
  7 Apr 2020 2 repositories listed
  To reduce the overwhelming size of Deep Neural Networks (DNN) teacher-student methodology tries to transfer knowledge from a complex teacher network to a simple student network.
• Neural Network Compression Framework for fast model inference
  20 Feb 2020 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF).
• The continuous categorical: a novel simplex-valued exponential family
  20 Feb 2020 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Simplex-valued data appear throughout statistics and machine learning, for example in the context of transfer learning and compression of deep networks.
• Distilled Split Deep Neural Networks for Edge-Assisted Real-Time Systems
  1 Oct 2019 2 repositories listed
  Offloading the execution of complex Deep Neural Networks (DNNs) models to compute-capable devices at the network edge, that is, edge servers, can significantly reduce capture-to-output delay.
• Forward and Backward Information Retention for Accurate Binary Neural Networks
  24 Sep 2019 2 repositories listed
  Our empirical study indicates that the quantization brings information loss in both forward and backward propagation, which is the bottleneck of training accurate binary neural networks.
• Learning Sparse Networks Using Targeted Dropout
  31 May 2019 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Before computing the gradients for each weight update, targeted dropout stochastically selects a set of units or weights to be dropped using a simple self-reinforcing sparsity criterion and then computes the gradients…
• ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
  5 Dec 2018 2 repositories listed Syntology ran 2 of 15 samples · 13 unverified
  The energy estimate model allows us to formulate DNN compression as a constrained optimization that minimizes the DNN loss function over the energy constraint.
• A Closer Look at Structured Pruning for Neural Network Compression
  10 Oct 2018 2 repositories listed
  Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducing the overall width of the network.
• Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
  30 Sep 2018 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements.
• Weightless: Lossy Weight Encoding For Deep Neural Network Compression
  13 Nov 2017 2 repositories listed
  This results in up to a 1.
• Diversity Networks: Neural Network Compression Using Determinantal Point Processes
  16 Nov 2015 2 repositories listed
  We introduce Divnet, a flexible technique for learning networks with diverse neurons.
• Certified Neural Approximations of Nonlinear Dynamics
  21 May 2025 1 repository listed
  Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, with the resulting neural approximations enabling verification and control of such systems.
• Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
  26 Sep 2024 1 repository listed Syntology ran 7 of 7 samples · 0 unverified
  In this work, we demonstrate the potential of large language models (LLMs) to act as gradient priors in a zero-shot setting.
• Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design
  2 May 2024 1 repository listed
  The limited degree of freedom in the current toolkit and the under-explored customization hinder the prototype ASIC or FPGA-based accelerator design.
• Towards Meta-Pruning via Optimal Transport
  12 Feb 2024 1 repository listed Syntology ran 5 of 5 samples · 0 unverified
  Structural pruning of neural networks conventionally relies on identifying and discarding less important neurons, a practice often resulting in significant accuracy loss that necessitates subsequent fine-tuning efforts.
• Causal-DFQ: Causality Guided Data-free Network Quantization
  24 Sep 2023 1 repository listed
  Inspired by the causal understanding, we propose the Causality-guided Data-free Network Quantization method, Causal-DFQ, to eliminate the reliance on data via approaching an equilibrium of causality-driven intervened…
• A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations
  13 Aug 2023 1 repository listed
  Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.
• Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
  13 Jun 2023 1 repository listed
  Neural network compression has been an increasingly important subject, not only due to its practical relevance, but also due to its theoretical implications, as there is an explicit connection between compressibility…
• Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
  25 May 2023 1 repository listed
  This representer theorem establishes that shallow vector-valued neural networks are the solutions to data-fitting problems over these infinite-dimensional spaces, where the network widths are bounded by the square of…
• SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers
  8 Apr 2023 1 repository listed
  In particular, fixed-point quantization is desirable to ease the computations using lightweight blocks, like adders and multipliers, of the underlying hardware.

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.