dawnranger

The neighborhood of each node in PSCAN should contain itself. The neighborhood of a vertex is defined in the paper of SCAN: >DEFINITION 1 (VERTEX STRUCTURE) Let v ∈ V,...

PSCAN cannot find communities

4

Hello, I try to find communities using PSCAN of sparking. Refering to the [doc of PSCAN](https://sparkling-graph.readthedocs.io/en/latest/comunities.html), I write the following codes : ``` val conf = new SparkConf().setAppName("pscan-test").setMaster("local") implicit val...

report the results on all datasets

7

Results of `node2vec`, `deewalk`, `line`, `sdne` and `struc2vec` on all datasets. Hope this will help anyone who is interested in this project. wiki | Alg | micro | macro |...

大量的简体字都是□

4

可能由于作者缺乏简体字的字体，导致chaizi-jt.txt中存在大量的□符号，能否补充一份可以正常显示这些文字的拆字字典？ 大约有2916个左右文字无法正常显示： 例如： 

I think the code is somehow disordered for two reasons: - set `dropout=0` right after `dropout=FLAGS.dropout` is meaningless - the updated `emb` should be returned rather than the untrained one

How is the performence compared to traditional community detection algorithms?

1

Nice work to follow. However, I didn't see the comparison against traditional community detection algorithms, such as louvain, LPA, infomap etc. Any opinions about the pros and cons between the...

time cost of 7b model training compared to AdamW

1

Does it means LOMO is 11 times faster than AdamW? 

请问下代码实现思路是什么？如何对齐python的模型结构和输出呢

2

是直接对照 huggingface 版的python代码来实现的吗 https://huggingface.co/THUDM/chatglm-6b-int8/blob/main/modeling_chatglm.py

Template should not be truncated

5

In the data preprocessing function, > https://github.com/hiyouga/LLaMA-Factory/blob/main/src/llmtuner/data/preprocess.py#L93 data is truncated after `encode_multiturn` if it's too long. However, some templates add special tokens after the query, which should not be truncated....