Layer-Assisted Neural Topic Modeling over Document Networks
Authors: Yiming Wang, Ximing Li, Jihong Ouyang
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results validate that LANTM significantly outperforms the existing models on topic quality, text classification and link prediction. |
| Researcher Affiliation | Academia | Yiming Wang1,2 , Ximing Li1,2 , Jihong Ouyang1,2 1College of Computer Science and Technology, Jilin University, China 2Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, China |
| Pseudocode | Yes | Algorithm 1 Training process for LANTM |
| Open Source Code | No | The paper provides GitHub links for several baseline models (e.g., NVDM, Prod LDA, ETM) in footnotes, but it does not provide a link or an explicit statement about the availability of the source code for their proposed LANTM model. |
| Open Datasets | Yes | In the experiments, we apply the dataset of Cora2 consisting of paper abstracts and citations [Mc Callum et al., 2000], and Reuters3 (R8) without any links. ...2http://people.cs.umass.edu/mccallum/data/cora-classify.tar.gz 3https://martin-thoma.com/nlp-reuters/ |
| Dataset Splits | Yes | In both transductive and inductive settings, we conduct 5-fold cross-validation experiments, and report the average scores of Micro-F1 and Macro-F1 in Table 3. ... Table 1: #doc #train #test |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions software like Adam optimizer, SVMs classifier (implying scikit-learn), and Palmetto for coherence measurement, but it does not provide specific version numbers for these software components. |
| Experiment Setup | Yes | Following [Kipf and Welling, 2016], we set three layers for both channels of MLP and GCN. ... For our LANTM, the combining coefficient ξ is tuned over {0.1, 0.2, . . . , 0.9}. For all baseline models, the default parameters are adopted. All methods are trained under same num of epochs and the topic numbers are set as {25, 50} for all datasets. ... For the topic number K, we vary it from the set of {25, 50, 75, 100, 125}. For combining coefficient ξ, we vary it from an increasing set {0.1, 0.2, . . . , 0.9}. |