Browse State-of-the-Art › Neural Network Compression
Neural Network Compression
77 papers with code · 1 benchmark · 1 dataset archive 2025-07-28
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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| CIFAR-10 (5 rows) | ShuffleNet – Quantised | Quantisation and Pruning for Neural Network Compression and Regularisation | code | — | Compare |
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
Papers archive 2025-07-28
archive papers tagged: 193 · with a code link: 77 · where Syntology ran a sample: 19 (16 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (19 of 193 tagged: 16 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 193, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
26 Oct 2021 3 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 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.
-
1 Jan 2020 3 repositories listed Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified (of 19 harvested samples) · 2 pointer-only (licence)Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0.
-
23 Aug 2019 3 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 3 pointer-only (licence)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.
-
2 Apr 2019 3 repositories listedLearning 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.
-
24 Mar 2019 3 repositories listedThe low-rank tensor approximation is very promising for the compression of deep neural networks.
-
28 Jan 2019 3 repositories listed Syntology official (archive's flag): 1 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples)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.
-
13 Feb 2017 3 repositories listedThe success of deep learning in numerous application domains created the de- sire to run and train them on mobile devices.
-
3 Oct 2022 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)We propose to minimize a generic differentiable objective with L₁ constraint using a simple reparametrization and straightforward stochastic gradient descent.
-
1 Feb 2022 2 repositories listed Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 17 harvested samples)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…
-
20 Nov 2020 2 repositories listedIn 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.
-
7 Apr 2020 2 repositories listedTo 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.
-
20 Feb 2020 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF).
-
20 Feb 2020 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 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.
-
1 Oct 2019 2 repositories listedOffloading 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.
-
24 Sep 2019 2 repositories listedOur 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.
-
31 May 2019 2 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 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…
-
5 Dec 2018 2 repositories listed Syntology 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 15 harvested samples)The energy estimate model allows us to formulate DNN compression as a constrained optimization that minimizes the DNN loss function over the energy constraint.
-
10 Oct 2018 2 repositories listedStructured 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.
-
30 Sep 2018 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)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.
-
13 Nov 2017 2 repositories listedThis results in up to a 1.
-
16 Nov 2015 2 repositories listedWe introduce Divnet, a flexible technique for learning networks with diverse neurons.
-
21 May 2025 1 repository listedNeural 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.
-
26 Sep 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)In this work, we demonstrate the potential of large language models (LLMs) to act as gradient priors in a zero-shot setting.
-
2 May 2024 1 repository listedThe limited degree of freedom in the current toolkit and the under-explored customization hinder the prototype ASIC or FPGA-based accelerator design.
-
12 Feb 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)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.
-
24 Sep 2023 1 repository listedInspired 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…
-
13 Aug 2023 1 repository listedModern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.
-
13 Jun 2023 1 repository listedNeural 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…
-
25 May 2023 1 repository listedThis 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…
-
8 Apr 2023 1 repository listedIn particular, fixed-point quantization is desirable to ease the computations using lightweight blocks, like adders and multipliers, of the underlying hardware.
-
16 Feb 2023 1 repository listed
-
30 Jan 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)
-
27 Dec 2022 1 repository listed
-
14 Dec 2022 1 repository listed
-
21 Jul 2022 1 repository listed
-
24 May 2022 1 repository listed
-
11 May 2022 1 repository listed
-
17 Jan 2022 1 repository listed
-
26 Oct 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
19 Oct 2021 1 repository listed
-
30 Sep 2021 1 repository listed
-
9 Jul 2021 1 repository listed
-
3 Jul 2021 1 repository listed
-
16 Jun 2021 1 repository listed
-
7 Jun 2021 1 repository listed
-
24 May 2021 1 repository listed
-
7 Mar 2021 1 repository listed
-
15 Feb 2021 1 repository listed
-
15 Feb 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 8 harvested samples) · 8 pointer-only (licence)
-
17 Dec 2020 1 repository listed
-
10 Dec 2020 1 repository listed
-
5 Dec 2020 1 repository listed
-
25 Nov 2020 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 16 unverified (of 26 harvested samples)
-
16 Nov 2020 1 repository listed
-
10 Nov 2020 1 repository listed
-
6 Oct 2020 1 repository listed
-
13 Jul 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)
-
15 Jun 2020 1 repository listed
-
29 Apr 2020 1 repository listed
-
20 Apr 2020 1 repository listed
-
29 Jan 2020 1 repository listed
-
14 Jan 2020 1 repository listed
-
6 Nov 2019 1 repository listed
-
14 Oct 2019 1 repository listed
-
7 Oct 2019 1 repository listed
-
30 Sep 2019 1 repository listed
-
27 Jul 2019 1 repository listed
-
23 Jul 2019 1 repository listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
25 Jun 2019 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 4 unverified (of 4 harvested samples)
-
7 Mar 2019 1 repository listed
-
26 Jan 2019 1 repository listed
-
5 Dec 2018 1 repository listed
-
30 Nov 2018 1 repository listed
-
20 Oct 2018 1 repository listed
-
19 Sep 2018 1 repository listed
-
6 Mar 2018 1 repository listed
-
11 Dec 2017 1 repository listed
-
Linearity-based neural network compression26 Jun 2025 0 repositories listed
-
MUC-G4: Minimal Unsat Core-Guided Incremental Verification for Deep Neural Network Compression3 Jun 2025 0 repositories listed
-
Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing22 May 2025 0 repositories listed
-
Low-Rank Matrix Approximation for Neural Network Compression25 Apr 2025 0 repositories listed
-
GranQ: Granular Zero-Shot Quantization with Channel-Wise Activation Scaling in QAT24 Mar 2025 0 repositories listed
-
Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix14 Mar 2025 0 repositories listed
-
Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding12 Feb 2025 0 repositories listed
-
A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks6 Jan 2025 0 repositories listed
-
What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias10 Oct 2024 0 repositories listed
-
Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching9 Oct 2024 0 repositories listed
-
Adaptive Error-Bounded Hierarchical Matrices for Efficient Neural Network Compression11 Sep 2024 0 repositories listed
-
TropNNC: Structured Neural Network Compression Using Tropical Geometry5 Sep 2024 0 repositories listed
-
Unified Framework for Neural Network Compression via Decomposition and Optimal Rank Selection5 Sep 2024 0 repositories listed
-
Convolutional Neural Network Compression Based on Low-Rank Decomposition29 Aug 2024 0 repositories listed
-
Condensed Sample-Guided Model Inversion for Knowledge Distillation25 Aug 2024 0 repositories listed
-
An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design2 Aug 2024 0 repositories listed
-
Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors16 Jul 2024 0 repositories listed
-
The Impact of Quantization and Pruning on Deep Reinforcement Learning Models5 Jul 2024 0 repositories listed
-
Neural Network Compression for Reinforcement Learning Tasks13 May 2024 0 repositories listed
-
Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space29 Feb 2024 0 repositories listed
-
SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field26 Feb 2024 0 repositories listed
-
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression31 Jan 2024 0 repositories listed
-
Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning15 Jan 2024 0 repositories listed
Syntology lines on 20 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections