Statistical Learning
GC-Bench: An Open and Unified Benchmark for Graph Condensation Appendix
We also provide public access to the official algorithm implementations. "KRR" is short for Kernel Ridge Regression and "CTC" is short for computation tree compression. "GNN" is short for Graph, "GNTK" is short for graph
GC-Bench: An Open and Unified Benchmark for Graph Condensation
The core concept of GC is to create a smaller, more manageable graph that retains the characteristics of the original graph.
Unified Graph Augmentations for Generalized Contrastive Learning on Graphs
Learning (GCL) frameworks are hampered by the specificity, complexity, and incompleteness of their GA techniques.
Why the Metric Backbone Preserves Community Structure
The metric backbone of a weighted graph is the union of all-pairs shortest paths.
Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
We also provide an extensive theoretical analysis of our methods.
Towards Exact Gradient-based Training on Analog In-memory Computing
While inference on analog accelerators has been studied recently, the training perspective is underexplored. Recent studies have shown that the "workhorse" of digital AI training - stochastic gradient descent (
Differentiable Quantum Computing for Large-scale Linear Control Connor Clayton
In this paper, we introduce an end-to-end quantum algorithm for linear-quadratic control with provable speedups.
Group Robust Preference Optimization in Reward-free RLHF
While these data often come from diverse labelers' groups (e.g., different demographics, ethnicities, company teams, etc.), traditional RLHF approaches