REVIEW 4 cited by
Do We Really Need Complicated Model Architectures For Temporal Networks?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Do We Really Need Complicated Model Architectures For Temporal Networks?
read the original abstract
Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning. Interestingly, we found that although both RNN and SAM could lead to a good performance, in practice neither of them is always necessary. In this paper, we propose GraphMixer, a conceptually and technically simple architecture that consists of three components: (1) a link-encoder that is only based on multi-layer perceptrons (MLP) to summarize the information from temporal links, (2) a node-encoder that is only based on neighbor mean-pooling to summarize node information, and (3) an MLP-based link classifier that performs link prediction based on the outputs of the encoders. Despite its simplicity, GraphMixer attains an outstanding performance on temporal link prediction benchmarks with faster convergence and better generalization performance. These results motivate us to rethink the importance of simpler model architecture.
Forward citations
Cited by 4 Pith papers
-
Graph Retention Networks for Dynamic Graphs
Graph Retention Networks extend retention to dynamic graphs to enable parallelizable training, O(1) inference, and chunkwise long-term training while delivering competitive performance with major efficiency gains.
-
Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
DSRD unifies temporal and structural adaptation for dynamic graphs via a single recurrent retentive state with learnable time-sensitivity parameters in the decay kernels.
-
A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
A2QTGN combines adaptive quantum amplitude encoding with a temporal graph network to improve dynamic link prediction, showing strong results on five benchmark datasets.
-
A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
A hybrid quantum-classical temporal graph network with adaptive amplitude encoding claims strong link-prediction results on five TGBL benchmarks, but the evaluation is undermined by a below-random baseline and missing code.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.