6 papers
Infinite Worlds from One Example: What Local Generators Must Share
Amin Najafgholizadeh, Mohsen Afsharchi
Seeded noise lets games generate any region of an unbounded world on demand. We ask what such a generator needs when every small window must come from one example, the constraint b…
Spectral Limits of Polynomial Graph Filters on the Long-Range Ising Model Benchmark
Amin Najafgholizadeh, Mohsen Afsharchi
The Long-Range Ising Model benchmark (LRIM) guarantees long-range dependence by construction: each label is the node's spin times the spin field convolved with a power-law coupling…
PATTERN Can Be Solved from Memory: Generator-Aware Baselines for Synthetic Node Classification
Amin Najafgholizadeh, Mohsen Afsharchi
PATTERN, a synthetic node-classification benchmark still used to rank graph networks, plants a random subgraph in a random host graph and asks which nodes belong to it. Its generat…
Fitting Every Hint Is Not Enough: Premature Floods in Recurrent Algorithmic Reasoners
Amin Najafgholizadeh, Mohsen Afsharchi
Recurrent algorithmic reasoners are trained with per-step hints on small graphs and run for many more steps on large ones. On breadth-first search in SALSA-CLRS, we find that a rea…
DADIR: Density-Aware Data-level Imbalanced Regression Framework
Shermin Shahbazi, Hossein Mohammadi, Mohsen Afsharchi
Imbalanced learning addresses predictive modeling problems with underrepresented regions of the data distribution. Although widely studied in classification, imbalanced regression…
Hybrid Imbalanced Regression Through Unified Data-Level and Algorithm-Level Balancing
Shermin Shahbazi, Hossein Mohammadi, Mohsen Afsharchi
Imbalanced learning is a critical challenge in machine learning, where underrepresented target values can bias models and degrade prediction performance on rare but important cases…