Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges
The DOI matches its Crossref record; 60 of the 67 references it cites were found in a registry or an index.
Abstract
In recent years, deep neural networks (DNNs) have received increased attention, have been applied to different applications, and achieved dramatic accuracy improvements in many tasks. These works rely on deep networks with millions or even billions of parameters, and the availability of graphics processing units (GPUs) with very high computation capability plays a key role in their success. For example, Krizhevsky et al. achieved breakthrough results in the 2012 ImageNet Challenge using a network containing 60 million parameters with five convolutional layers and three fully connected layers. Usually, it takes two to three days to train the whole model on the ImagetNet data set with an NVIDIA K40 machine. In another example, the top face-verification results from the Labeled Faces in the Wild (LFW) data set were obtained with networks containing hundreds of millions of parameters, using a mix of convolutional, locally connected, and fully connected layers. It is also very time-consuming to train such a model to obtain a reasonable performance. In architectures that only rely on fully connected layers, the number of parameters can grow to billions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“but there is no review discussing all three categories which in future will be integrated seamlessly to design effective and efficient DNNs in the new edge intelligence era.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [26]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Recently, more state-of-the-art architectures are used as baseline models in many works, including network in networks [67], VGGNets [68], and ResNets [69].”
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 4×
“[1] achieved breakthrough results in the 2012 ImageNet Challenge using a network containing 60 million parameters with five convolutional layers and three fully-connected layers.”
MethodInfluentialGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
“Other popular standard models include LeNets [66], All-CNN-nets [67] and many others.”
MethodDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 1×
“The work in [51] introduced a KD compression framework, which eased the training of deep networks by following a student-teacher paradigm, in which the student was penalized according to a softened version of the teacher’s output.”
BackgroundDeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · cited 1×
“example is the top face verification results on the Labeled Faces in the Wild (LFW) dataset were obtained with networks containing hundreds of millions of parameters, using a mix of convolutional, locally-connected, and fully-connected layers [2], [3].”
MethodLarge Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · neural information processing systems · Cited by 4,489
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408 · cited 2×
“works that directly train CNNs with binary weights, for instance, BinaryConnect [13], BinaryNet [14] and XNORNetworks [15].”
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447 · cited 2×
“Other popular standard models include LeNets [66], All-CNN-nets [67] and many others.”
MethodPruning Filters for Efficient ConvNets
Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2016) · arXiv · doi:10.48550/arxiv.1608.08710 · Cited by 2,928 · cited 1×
“The work in [29] used l1-norm to select and prune unimportant filters.”
MethodFitNets: Hints for Thin Deep Nets
Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.6550 · Cited by 2,859 · cited 1×
“The work in [52] aimed to address the network”
BackgroundDeep Networks with Stochastic Depth
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_39 · Cited by 2,104
Deep Learning with Limited Numerical Precision
Gupta, S., Agrawal, A., Gopalakrishnan, K., & Narayanan, P. (2015) · International Conference on Machine Learning · Cited by 1,590
(1993) · CaltechAUTHORS (California Institute of Technology) · Cited by 1,498
Learning to learn by gradient descent by gradient descent
Andrychowicz, M., Denil, M., Gomez, S., Hoffman, M. W., Pfau, D., Schaul, T., Shillingford, B., & de Freitas, N. (2016) · arXiv · doi:10.48550/arxiv.1606.04474 · Cited by 1,486 · cited 1×
“To solve the first problem, we can rely on the recent learning-to-learn strategy [72], [73].”
MethodExploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
Denton, R., Zaremba, W., Bruna, J., LeCun, Y., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1404.0736 · Cited by 1,414 · cited 1×
“In [36], a few low-rank approximation and clustering schemes for the convolutional kernels were proposed.”
BackgroundDo Deep Nets Really Need to be Deep?
Ba, J. L., & Caruana, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6184 · Cited by 1,335
Quantized Convolutional Neural Networks for Mobile Devices
Wu, J., Leng, C., Wang, Y., Hu, Q., & Cheng, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.521 · Cited by 1,212
Speeding up Convolutional Neural Networks with Low Rank Expansions
Jaderberg, M., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.88 · Cited by 1,164
Compressing Neural Networks with the Hashing Trick
Chen, W., Wilson, J. T., Tyree, S., Weinberger, K. Q., & Chen, Y. (2015) · arXiv · doi:10.48550/arxiv.1504.04788 · Cited by 974 · cited 1×
“[24] proposed a HashedNets model that used a low-cost hash function to group weights into hash buckets for parameter sharing.”
Method(2014) · arXiv (Cornell University) · Cited by 942
Deeply learned face representations are sparse, selective, and robust
Sun, Y., Wang, X., & Tang, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298907 · Cited by 939
Compressing Deep Convolutional Networks using Vector Quantization
Gong, Y., Liu, L., Yang, M., & Bourdev, L. D. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6115 · Cited by 925 · cited 1×
“Parameter pruning and sharing An early work that showed that network pruning is effective in reducing the network complexity and addressed the overfitting problem is [6].”
BackgroundFast Algorithms for Convolutional Neural Networks
Lavin, A., & Gray, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.435 · Cited by 915 · cited 1×
“Other approaches to reduce the convolutional overheads include using FFT based convolutions [63] and fast convolution using the Winograd algorithm [64].”
MethodZhu, C., Han, S., Mao, H., & Dally, W. J. (2016) · arXiv · doi:10.48550/arxiv.1612.01064 · Cited by 865 · cited 1×
“A novel quantization framework was introduced in [12], which reduced the precision of network weights to ternary values.”
MethodComparing Biases for Minimal Network Construction with Back-Propagation
Hanson, S. J., & Pratt, L. (1988) · neural information processing systems · Cited by 738
(2011) · Cited by 713
Wu, B., Wan, A., Iandola, F., Jin, P. H., & Keutzer, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.60 · Cited by 614 · cited 2×
“SqueezeNet [48] was proposed to replace 3 × 3 convolution with 1 × 1 convolution, which created a compact neural network with”
MethodLow-rank matrix factorization for Deep Neural Network training with high-dimensional output targets
Sainath, T. N., Kingsbury, B., Sindhwani, V., Arisoy, E., & Ramabhadran, B. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638949 · Cited by 593
Group Equivariant Convolutional Networks
Cohen, T., & Welling, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.07576 · Cited by 524 · cited 3×
“The idea of using transferred convolutional filters to compress CNN models is motivated by recent works in [42], which introduced the equivariant group theory.”
BackgroundMethodData-free Parameter Pruning for Deep Neural Networks
Srinivas, S., & Babu, R. V. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.31 · Cited by 505 · cited 2×
“For example, Srinivas and Babu [22] explored the redundancy among neurons, and proposed a data-free pruning method to remove redundant neurons.”
MethodBinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1Preprint
Courbariaux, M., & Bengio, Y. (2016) · arXiv (Cornell University) · Cited by 484
Predicting Parameters in Deep Learning
Shakibi, B. (2014) · University of British Columbia · doi:10.14288/1.0165555 · Cited by 462
Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition
Wu, D., Pigou, L., Kindermans, P.-J., Le, N. D.-H., Shao, L., Dambre, J., & Odobez, J.-M. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2537340 · Cited by 453 · cited 1×
“In [59], dynamic deep neural networks (D2NN) were introduced, which were a type of feed-forward deep neural network that selected and executed a subset of D2NN neurons based on the input.”
MethodLearning Structured Sparsity in Deep Neural Networks
Wen, W. X., Wu, C., Wang, Y., Chen, Y., & Li, H. H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.03665 · Cited by 402 · cited 1×
“[28] added a structured sparsity regularizer on each layer to reduce trivial filters, channels or even layers.”
BackgroundFast ConvNets Using Group-Wise Brain Damage
Lebedev, V., & Lempitsky, V. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.280 · Cited by 373 · cited 1×
“The work in [26] imposed group sparsity constraint on the convolutional filters to achieve structured”
BackgroundFast Training of Convolutional Networks through FFTs
Mathieu, M., Henaff, M., & LeCun, Y. (2014) · International Conference on Learning Representations · Cited by 347
Convolutional neural networks with low-rank regularization
Tai, C., Xiao, T., Zhang, Y., Wang, X., & Weinan, E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06067 · Cited by 341 · cited 5×
“Baseline Models Representative Works Alexnet [1] structural matrix [30]–[32] low-rank factorization [39] Network in network [68] low-rank factorization [39] VGG nets [69] transfered filters [43] low-rank factorization [39] Residual networks [70] compact filters [48], stochastic depth [61] parameter sharing [25] All-CN…”
BackgroundMethodInfluentialAn Exploration of Parameter Redundancy in Deep Networks with Circulant Projections
Cheng, Y., Yu, F. X., Feris, R. S., Kumar, S., Choudhary, A., & Chang, S.-F. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.327 · Cited by 303
Self-citationLess Is More: Towards Compact CNNs
Zhou, H., Alvarez, J. M., & Porikli, F. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_40 · Cited by 279 · cited 1×
“In [27], a group-sparse regularizer on neurons was introduced during the training stage to learn compact CNNs with reduced filters.”
Yang, Z., Moczulski, M., Denil, M., De Freitas, N., Song, L., & Wang, Z. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.173 · Cited by 215 · cited 1×
“In [31], a novel Adaptive Fastfood transform was introduced to reparameterize the matrix-vector multiplication of fully connected layers.”
MethodRigamonti, R., Sironi, A., Lepetit, V., & Fua, P. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.355 · Cited by 205 · cited 1×
“[35] suggested learning separable 1-D filters.”
Face Model Compression by Distilling Knowledge from Neurons
Luo, P., Zhu, Z., Liu, Z., Wang, X., & Tang, X. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10449 · Cited by 199 · cited 1×
“works which represented the knowledge using the soften label probabilities, [54] represented the knowledge by using the neurons in the higher hidden layer, which preserved as much information as the label probabilities, but are more compact.”
MethodKorattikara, A., Rathod, V., Murphy, K., & Welling, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.04416 · Cited by 182 · cited 1×
“The work in [53] trained a parametric student model to approximate a Monte Carlo teacher.”
MethodLearning the Number of Neurons in Deep Networks
Álvarez, J. M., & Salzmann, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.06321 · Cited by 164 · cited 1×
“One possible solution is to use the training-based channel pruning methods [74], which focus on imposing sparse constraints on weights during training, and could adaptively”
MethodUnderstanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units
Shang, W., Sohn, K., Almeida, D., & Lee, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.05201 · Cited by 162 · cited 3×
“For example, the work in [44] found that the lower convolution layers of CNNs learned redundant filters to extract both positive and negative phase information of an input signal, and defined T (·) to be the simple negation function:”
BackgroundMethodLoss-aware Binarization of Deep Networks
Hou, L., Yao, Q., & Kwok, J. T.-Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01600 · Cited by 150 · cited 1×
“To address this issue, the work in [17] proposed a proximal Newton algorithm with diagonal Hessian approximation that directly minimizes the loss with respect to the binary”
MethodExploiting Cyclic Symmetry in Convolutional Neural Networks
Dieleman, S., Fauw, J. D., & Kavukcuoglu, K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02660 · Cited by 149 · cited 2×
“The work in [46] considered a combination of rotation by a multiple of 90◦ and”
BackgroundNet2Net: Accelerating Learning via Knowledge Transfer
Chen, T., Goodfellow, I., & Shlens, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05641 · Cited by 143 · cited 1×
“The work in [55] accelerated the experimentation process by instantaneously transferring the knowledge from a previous”
BackgroundTowards the Limit of Network Quantization
Choi, Y., El-Khamy, M., & Lee, J. (2016) · arXiv · doi:10.48550/arxiv.1612.01543 · Cited by 143 · cited 1×
“It was shown in [11] that Hessian weight could be used to measure the importance of network parameters, and proposed to minimize Hessian-weighted quantization errors in average for clustering network parameters.”
MethodNeural Networks with Few Multiplications
Lin, Z., Courbariaux, M., Memisevic, R., & Bengio, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.03009 · Cited by 141 · cited 1×
“The work in [18] significantly reduced the time on float point multiplication in the training stage by stochastically binarizing weights and converting multiplications in the hidden state computation to sign changes.”
BackgroundCompression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
Kim, Y., Park, E., Yoo, S., Choi, T., Lu, Y., & Shin, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06530 · Cited by 111 · cited 1×
“The work in [76] proposed a one-shot whole network compression scheme consisting of three components: rank selection, lowrank tensor decomposition, and fine-tuning to make deep CNNs work in mobile.”
BackgroundGeneralized Displacement Structure for Block-Toeplitz, Toeplitz-Block, and Toeplitz-Derived Matrices
Kailath, T., & Chun, J. (1994) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/s0895479889169042 · Cited by 102 · cited 1×
“Their proposed method can be extended to various other structured matrix classes, including block and multilevel Toeplitz-like [33] matrices related to multidimensional convolution [34].”
MethodStructured Transforms for Small-Footprint Deep Learning
Sindhwani, V., Sainath, T. N., & Kumar, S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.01722 · Cited by 93 · cited 2×
“The work in [32] showed the effectiveness of the new notion of parsimony in the theory of structured matrices.”
BackgroundMethodDeep neural networks are robust to weight binarization and other non-linear distortions
Merolla, P. A., Appuswamy, R., Arthur, J. V., Esser, S. K., & Modha, D. S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.01981 · Cited by 74 · cited 1×
“The systematic study in [16] showed that networks trained with backpropagation could be robust against (robust against or resilient to) specific weight distortions, including binary weights.”
BackgroundSoft Weight-Sharing for Neural Network Compression
Ullrich, K., Meeds, E., & Welling, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.04008 · Cited by 72 · cited 2×
“In [25], a simple regularization method based on soft weight-sharing was proposed, which included”
MethodBeyond filters: Compact feature map for portable deep model
Wang, Y., Xu, C., & Tao, D. (2017) · OPUS - Open Publications of UTS Scholars (University of Technology Sydney) · Cited by 59
Doubly Convolutional Neural NetworksPreprint
Zhai, S., Cheng, Y., Lu, W., & Zhang, Z. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.09716 · Cited by 55 · cited 3×
“Baseline Models Representative Works Alexnet [1] structural matrix [30]–[32] low-rank factorization [39] Network in network [68] low-rank factorization [39] VGG nets [69] transfered filters [43] low-rank factorization [39] Residual networks [70] compact filters [48], stochastic depth [61] parameter sharing [25] All-CN…”
BackgroundMethodSelf-citationFast Multidimensional Convolution in Low-Rank Tensor Formats via Cross Approximation
Rakhuba, M., & Oseledets, I. V. (2015) · SIAM Journal on Scientific Computing · doi:10.1137/140958529 · Cited by 53 · cited 1×
“Their proposed method can be extended to various other structured matrix classes, including block and multilevel Toeplitz-like [33] matrices related to multidimensional convolution [34].”
MethodMulti-Bias Non-linear Activation in Deep Neural Networks
Li, H., Ouyang, W., & Wang, X. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.00676 · Cited by 45 · cited 1×
“In [45], it was observed that magnitudes of the responses”
Background
Cited by
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
Knowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965
Deep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2904897 · Cited by 1,768
Metadata
- Authors
- Cheng, Y., Wang, D., Zhou, P., & Zhang, T.
- Affiliations
- IBM Research - Thomas J. Watson Research Center (US)
- Harbin Institute of Technology (CN)
- Huazhong University of Science and Technology (CN)
- Tsinghua University (CN)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2018-01
- Volume
- 35
- Issue
- 1
- Pages
- 126-136
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W2783538964
- Cited by
- 817
- References
- 67
- Citations by year
- 2026: 114 · 2025: 132 · 2024: 116 · 2023: 110 · 2022: 109 · 2021: 92 · 2020: 89 · 2019: 41 · 2018: 14
- FWCI
- 29.51
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- model compression, deep neural network, inference acceleration, parameter reduction, convolutional neural networks, training efficiency, GPU computing, face verification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.