4 papers
ARIA: A Diagnostic Framework for Music Training Data Attribution
Changheon Han, Ashkan Panahi, Kıvanç Tatar
Training data attribution (TDA) for music generation must answer two questions that copyright analysis requires, namely which training songs influence a generated output and along…
A Gaussian Comparison Theorem for Training Dynamics in Machine Learning
Ashkan Panahi
We study training algorithms with data following a Gaussian mixture model. For a specific family of such algorithms, we present a non-asymptotic result, connecting the evolution of…
Subgraph Federated Learning via Spectral Methods
Javad Aliakbari, Johan Ãstman, Ashkan Panahi +1
We consider the problem of federated learning (FL) with graph-structured data distributed across multiple clients. In particular, we address the prevalent scenario of interconnecte…
Bounds on Perfect Node Classification: A Convex Graph Clustering Perspective
Firooz Shahriari-Mehr, Javad Aliakbari, Alexandre Graell i Amat +1
We present an analysis of the transductive node classification problem, where the underlying graph consists of communities that agree with the node labels and node features. For no…