Data to 7 Oct 2026

Deep Differentiable Logic Gate Networks

arXiv 2210.08277 ↗First posted 15 Oct 2022cs.LGcited by 67

Not on the map. Why?

Abstract (arXiv)

Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learning combinations of logic gates. These networks comprise logic gates such as "AND" and "XOR", which allow for very fast execution. The difficulty in learning logic gate networks is that they are conventionally non-differentiable and therefore do not allow training with gradient descent. Thus, to allow for effective training, we propose differentiable logic gate networks, an architecture that combines real-valued logics and a continuously parameterized relaxation of the network. The resulting discretized logic gate networks achieve fast inference speeds, e.g., beyond a million images of MNIST per second on a single CPU core.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 33 of its 79 references that are in the map. First posted on arXiv 15 Oct 2022.

Builds on

33 of 79 references.

References · 33

2014Adam: A Method for Stochastic Optimizationcited by 36,960
2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
2020What is the State of Neural Network Pruning?cited by 578
2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
2015Deep Learning with Limited Numerical Precisioncited by 368
2017Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Sciencecited by 325
2017Variational Dropout Sparsifies Deep Neural Networkscited by 265

21 more

2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 265
2020Binary Neural Networks: A Surveycited by 184
2016FINN: A Framework for Fast, Scalable Binarized Neural Network Inferencecited by 141
2019Differentiable Ranks and Sorting using Optimal Transportcited by 113
2020Analyzing Differentiable Fuzzy Logic Operatorscited by 100
2022The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Trainingcited by 85
2019Machine Learning at the Network Edge: A Surveycited by 83
2020Learning with Differentiable Perturbed Optimizerscited by 81
2019Weight Agnostic Neural Networkscited by 71
2021Effective Sparsification of Neural Networks with Global Sparsity Constraintcited by 45
2019PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfigurationcited by 41
2021Differentiable Sorting Networks for Scalable Sorting and Ranking Supervisioncited by 31
2022Monotonic Differentiable Sorting Networkscited by 25
2021Learning with Algorithmic Supervision via Continuous Relaxationscited by 21
2021Differentiable Logic Machinescited by 18
2022GenDR: A Generalized Differentiable Renderercited by 12
2020Learning Binary Decision Trees by Argmin Differentiationcited by 11
2022Learning with Differentiable Algorithmscited by 10
2020Learning Symbolic Expressions via Gumbel-Max Equation Learner Networkscited by 8
2019A Standalone FPGA-based Miner for Lyra2REv2 Cryptocurrenciescited by 1
2020Making Logic Learnable With Neural Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 8; 2025: 23; 2026: 32.

67 papers.

Sort:

By area:

2023Interpretable Neural-Symbolic Concept Reasoningcited by 56
2023Learning Transformer Programscited by 40
2024Convolutional Differentiable Logic Gate Networkscited by 37
2024Differentiable Weightless Neural Networkscited by 27
2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
2024Uncertainty Quantification via Stable Distribution Propagationcited by 10
2024Learning Interpretable Differentiable Logic Networkscited by 10
2025Differentiable Logic Cellular Automata: From Game of Life to Pattern Generationcited by 9
2025Light Differentiable Logic Gate Networkscited by 9
2025Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfactioncited by 6
2025WARP-LUTs -- Walsh-Assisted Relaxation for Probabilistic Look Up Tablescited by 6
2025LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deploymentcited by 6

38 more

2025A Method for Optimizing Connections in Differentiable Logic Gate Networkscited by 5
2025LogicCBMs: Logic-Enhanced Concept-Based Learningcited by 5
2024Improving Discrete Optimisation Via Decoupled Straight-Through Estimatorcited by 4
2025Logic Gate Neural Networks are Good for Verificationcited by 4
2025NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNNcited by 4
2025Scalable Interconnect Learning in Boolean Networkscited by 4
2025A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoningcited by 4
2024BOLD: Boolean Logic Deep Learningcited by 3
2024Towards Narrowing the Generalization Gap in Deep Boolean Networkscited by 3
2025eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networkscited by 3
2025LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neuronscited by 3
2025Compact Rule-Based Classifier Learning via Gradient Descentcited by 2
2025Learning Interpretable Differentiable Logic Networks for Tabular Regressioncited by 2
2026WARP Logic Neural Networkscited by 2
2026Learning with Boolean threshold functionscited by 2
2026Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networkscited by 2
2026Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networkscited by 2
2026Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectorscited by 2
2026Legible-by-Construction: Attention and End-to-End Transformerscited by 2
2023Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environmentscited by 1
2025From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networkscited by 1
2025Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Controlcited by 1
2026Inter-patient ECG Arrhythmia Classification with LGNs and LUTNscited by 1
2026Differentiable Logic Synthesis: Spectral Coefficient Selection via Sinkhorn-Constrained Compositioncited by 1
2026Learning Compact Boolean Networkscited by 1
2026BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networkscited by 1
2026The Banach-Butterfly Invariant: Influence-Adaptive Walsh Geometry for Ternary Polynomial Threshold Functionscited by 1
2026LogicIR: Logic Gate Networks for Image Restorationcited by 1
2026FPGN: Redefining Ultra-Fast Programmable Gate-based Neural Acceleration with Differentiable LUTscited by 1
2026Self-Organising Digital Circuitscited by 1
2023Towards Understanding Gradient Approximation in Equality Constrained Deep Declarative Networkscited by 0
2024Interpretable Classification via a Rule Network with Selective Logical Operatorscited by 0
2025GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learningcited by 0
2025Learning Interpretable Differentiable Logic Networks for Time-Series Classificationcited by 0
2025Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integrationcited by 0
2025A Framework Based on Graph Cellular Automata for Similarity Evaluation in Urban Spatial Networkscited by 0
2025Gate-level boolean evolutionary geometric attention neural networkscited by 0
2026Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligencecited by 0

50 most cited of 67 All 67 (JSON)