- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper proposes a Backward Knowledge Feedback via Parameter Expansion (DBKF-PE) method for dynamic graph learning. DBKF-PE incorporates parameter expansion to alleviate knowledge squeezing and backward knowledge feedback to ensure model performance on historical graphs. The proposed method is evaluated on six public datasets and shows improved results.
Critical strengths
- The idea of using newly learned graph knowledge to improve performance on historical graphs is interesting and worth exploring.
- The experiments cover multiple datasets and downstream tasks, with generally competitive results against existing methods.
Critical weaknesses
- Eq. (1) is confusing. If represents the unchanged part of relative to , then should be defined relative to . It is unclear why can be used to construct . In addition, where should the edges between and be?
- The motivation behind Eq. (2) is unclear. Why does the model minimize the loss on the entire graph while maximizing the loss on the changed subgraph? It is also unclear why the authors cannot simply optimize the GNN on the unchanged subgraph. It is unclear what parameters are being expanded; are they additional GNN layers, higher-dimensional vectors, or something else? The paper needs to define the expansion clearly.
- The parameter freezing strategy seems inconsistent. Section 3.2 claims that freezing historical parameters prevents catastrophic forgetting, but Section 3.3 allows these parameters to be updated. This raises questions about how the method actually prevents forgetting.
- The paper is not well-written and is very difficult to follow.
Questions for authors
- What is the definition of ?
- What is the rationale for Eq. (2)?
- What are the expanded model parameters?
- Can your method deal with node/edge deletion?