Patent Citation Dynamics Modeling via Multi-Attention Recurrent Networks
Authors: Taoran Ji, Zhiqian Chen, Nathan Self, Kaiqun Fu, Chang-Tien Lu, Naren Ramakrishnan
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on a large patent citation dataset collected from USPTO demonstrate that the proposed model outperforms state-of-the-art models at forward citation forecasting. |
| Researcher Affiliation | Academia | Taoran Ji1,2 , Zhiqian Chen1,2 , Nathan Self1,2 , Kaiqun Fu1,2 , Chang-Tien Lu1,2 and Naren Ramakrishnan1,2 1Discovery Analytics Center, Virginia Tech, Arlington, VA 22203, USA 2Department of Computer Science, Virginia Tech, Arlington, VA 22203, USA {jtr, czq, nwself, fukaiqun, ctlu}@vt.edu, naren@cs.vt.edu |
| Pseudocode | No | The paper describes the model in detail using text and mathematical equations, but it does not include any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our dataset and code is publicly available for download.2 (Footnote 2: https://github.com/TaoranJ/PC-RNN) |
| Open Datasets | Yes | Our dataset originates from the publicly accessible PatentsView1 database which contains more than 6 million U.S. patents. (footnote 1: http://www.patentsview.org/download/) |
| Dataset Splits | No | The paper states, 'we sampled 15,000 sequences of which 12,000 sequences are used for the training set and the remaining 3,000 sequences are the test set.' It does not explicitly mention a distinct validation set or its split details. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware specifications (e.g., CPU, GPU models, memory) used to conduct the experiments. |
| Software Dependencies | No | The paper mentions the use of LSTMs and the ADAM optimizer, but it does not specify any version numbers for programming languages, libraries, or frameworks used (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | In our experiments, the dimension of the hidden state of the patent sequence encoder and decoder is set to 32 and is 16 for assignee and inventor sequence encoders. The total loss is the sum of the time prediction loss and the cross-entropy loss for the patent category prediction: ... We adopted the ADAM [Kingma and Ba, 2014] optimizer for training. |