ZigZag Persistence as a Measure of Topology Preservation in Temporal Link Prediction
Abstract not provided.
Publications
Search results
Jump to search filtersArbitrary Autoencoder Injection for Interpretability Experimentation
Goes over a simple software library (Python) for utilizing sparse autoencoders for more models than just language models.
Zigzag Persistence as a Measure of Topology Preservation in Temporal Link Prediction
Abstract not provided.
Graph Attention Embeddings as a Causal Lens in Temporal Link Prediction
Abstract not provided.
Topological Preservation in Temporal Link Prediction
Poster presentation for the Student Intern Symposium introducing zig-zag persistence (ZZP) and a minor result showing that a temporal link prediction model was able to create a representation which preserved the dynamic topology of the trained data.
5 Results