Yang's research group wiki

User Tools

Site Tools

Trace:
volunteer_data:top

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
volunteer_data:top [2022/04/15 02:09] – timvolunteer_data:top [2024/03/17 22:56] (current) – yang
Line 1: Line 1:
 ====== Volunteer Data Analysis ====== ====== Volunteer Data Analysis ======
  
 +====Volunteer Matching====
  
-**Meeting: Jan 17, 2022** +  * [[volunteer_data:volunteer_matching| Project Page]]
-  * Presented results of experiments on Volunteer data and Movielens +
-  * Discussed the metrics for measuring performance on the two datasets +
-  * Showed graphs of two methods and their performance on the two datasets+
  
-  * Key: the BOA method still outperforms LDA in both datasets.+====Persistent community detection====
  
 +  * [[volunteer_data:tda_review|TDA Literature Review]]
  
-  * **Comments and Future work** +====Recommendation and social network analysis====
-  * To compute metrics as a whole and not aggregate them separately for each user. +
-  * To apply BOA method on a recommendation paper and compare the results +
-  * To compile a representative code and send to the professor +
-  * To read literature on latest work in RS.+
  
-**Meeting: Jan 24, 2022** +  * [[volunteer_data:meetings| Meeting Notes]]
-  * Discussed the possible alternatives of embedding the data, social net embedding +
-  * Refined the life document to include user history pertaining to time, location and participation history +
-  * Discussed a few papers that have used GNN for prediction +
- +
-  * **Comments and Future work** +
-  * To read the papers related to Social Recommendation eg, Song et al (2019) +
-  * Understand the nature of embeddings they used for the input data +
-  * Summarise findings of papers (using GNN) whose data is similar to ours  +
- +
-**Meeting: Feb 18, 2022** +
-  * Presented a Survey on GNN Social recommendation +
-  * Presented Item-to-Item KNN method used by Amazon +
-  * Discussed two papers on Social Recommendation and presented their findings  +
-  * Paper 1: GNN for Social Recommendation - Fan, Ma,  Li, He,Zhao,Tang, and Yin. 2019. (ACM, WWW) +
-  * Paper 2: Session-based Social Recommendation via Dynamic Graph Attention Networks, Song, Wang and Xiao (2019) – (ACM, WSDM)  +
- +
- +
-  * **Comments and Future work** +
-  * To begin working on experiments related to dynamic session-based recommendation +
-  * To make a list of the features and embeddings that can be used from our data,  +
-  * Determine session and neighbours based on our data, eg location based or participation based. +
- +
- +
-**Meeting: March 1, 2022** +
-  * **Attendees:** +
-  * Professor Yang Li, Shutong and Tim (19:00-20:00) +
-  * **Discussion** +
-  * Tim presented a proposal on GNN +
- +
-  * **Comments and Future work** +
-  * To clarify the research problem by formulating the underlying mathematical nitty gritties +
-  * To consider geographic location and tasks types as input features and determine how to incorporate them +
- +
-**Meeting: March 23, 2022** +
-  * **Attendees:** +
-  * Professor Yang Li, Shutong and Tim (11:00-12:00) +
-  * **Discussion** +
-  * Shutong presented and discussed the plan on how the experiments will be conducted. +
-  * Tim presented the findings on the first experiment for Session based GNN +
- +
-  * **Comments and Future work** +
-  * Tim to write a brief methodology discussing his implementation of the algorithm +
-  * Need for providing details for experimental plan and hyper-parameter tuning +
- +
- +
-**Meeting: March 31, 2022** +
-  * **Attendees:** +
-  * Professor Yang Li, Shutong and Tim (11:00-12:00) +
-  * **Discussion** +
-  * Tim presented a write up of methodology section that also included experiment plan +
-  * **Comments and Future work** +
-  * Tim to give more clarity on the network architecture diagram  +
-  * To consider node embeddings as one hot key vectors +
-  * To also include task type information on the volunteer preference +
-  * Tim to remind Shutong and the professor every week before each meeting. +
-  * Shutong suggested Tim to use PPT to draw flowchart and diagrams +
-  * Shutong suggested to provide reference code for matching task types +
- +
- +
-**Meeting: April 7, 2022** +
-  * **Attendees:** +
-  * Professor Yang Li, Shutong and Tim (11:00-12:00) +
-  * **Discussion** +
-  * Shutong presented her preliminary experimental results +
-  * Tim discussed the DGRec framework.  +
-  * **Comments and Future work** +
-  *Shutong to continue with her experimental plan +
-  *Shutong to consider narrowing the research towards a more specific problem +
-  * Tim to conduct experiment and reproduce the results in the paper +
-  * **Attachments:** +
-  * {{:volunteer_data:shutong_experiments.pptx}} +
-  * {{:volunteer_data:graph_attention_network.docx}} +
- +
-**Meeting: April 14, 2022** +
-  * **Attendees:** +
-  * Professor Yang Li, Shutong and Tim (11:00-12:00) +
-  * **Discussion** +
-  * Shutong presented statistical data for Pioneers to be used in an article +
-  * Tim presented the reproduced results from the paper +
-  * **Comments and Future work** +
-  *Shutong to write a summary of her latest findings  +
-  * Tim to consider a naive baseline approach that will be compared against the current method +
-  * **Attachments:** +
-  * {{ :volunteer_data:tim_progress_4.14.pptx |}}+
  
volunteer_data/top.1650002975.txt.gz · Last modified: 2022/04/15 02:09 by tim