This work introduces SHAKE-GNN, a novel scalable graph-level GNN framework based on a hierarchy of Kirchhoff Forests, a class of random spanning forests used to construct stochastic multi-resolution decompositions of graphs, enabling flexible trade-offs between efficiency and performance.
The empirical evaluations on standard benchmarks and in a comparison study with widely used explanation methods show that attention weights can be meaningfully incorporated into the studied XAI frameworks, highlighting their value in enriching transformer explainability.
Marte Eggen, Jacob Lysnæs-Larsen, Inga Strümke· arXiv.org· 1 citation
The teacher, an auxiliary behavior model, is trained to sample high-loss regions of the student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum.
Minsu Kim, Sanghyeok Choi, Taeyoung Yun et al.· International Conference on...· 27 citations· ⚡6
It is established that gradient-based training can induce an implicit regularization towards low rank for several neural network architectures, and it is demonstrated empirically that this phenomenon may facilitate an explanation of generalization over natural data.
Noam Razin· arXiv.org· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
A new algorithm for amortized inference in sparse probabilistic graphical models (PGMs) is presented that enables off-policy training but avoids the need to instantiate all the random variables for each parameter update, thus speeding up training considerably.
J. Falet, Haebeom Lee, Esmeralda S. Whitammer et al.· International Conference on...· 9 citations
This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs. We demon...
Esmeralda S. Whitammer, S. Lahlou, T. Deleu et al.· International Conference on...· 120 citations· ⚡9
A general framework for implementing NMMs using Template Model Builder (TMB), which automatically integrates out random effects and evaluates the marginal objective function alongside its exact gradients, eliminating the need for manual derivations or ad hoc approximations.
Nan Zheng, H. Cheung, Vibhu Sharma et al.· 0 citations
This work presents a framework for learning continuous latent representations of admissible partial differential equations by embedding a scientific inductive bias directly into the training distribution, and shows that embedding a scientific inductive bias in the training distribution enables the learning of compact a...
A classification-weighted generalized-eigenvalue criterion is developed under which informative partial classification may have smaller asymptotic classification risk without globally dominating complete classification in Fisher information.
Fariborz Setoudehtazang, Geoffrey J. McLachlan· 0 citations
Direct first-order jackknife cancellation and exact-LOO concentration control deletion-to-full risk transfer and fluctuation, respectively, completing recovery of the conditional population-risk curve are estimated.
This work proposes a new design of fair classifiers for multi-class classification problems in the presence of vector-valued sensitive attributes and proposes a specialized numerical method for solving the resulting optimization problem.
A statistical framework connecting token prediction with representation geometry, encoder approximation, and downstream performance is developed, introducing a self-consistency principle showing that repeated applications of a shared representation block can progressively refine the contextual representation without in...
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
