ShaplEIG introduces a Bayesian experimental design framework to efficiently and adaptively estimate Shapley values by minimizing the number of required costly function evaluations.

The paper proposes a semi-relaxed Gromov-Wasserstein objective to estimate the latent connectivity structure of large-scale networks, achieving statistically consistent and efficient recovery of the u…

The paper analyzes low-degree estimation thresholds for recovering hidden signals in planted hypergraphs and tensor PCA, establishing sharp phase transitions and providing polynomial-time recovery alg…

This paper introduces BBOmix, an open-source benchmark for unsupervised representation learning on real-world biological data.

The paper introduces SGAP-PPIS, a structure-guided adaptive propagation model that improves protein-protein interaction site prediction by allowing information diffusion to adapt based on a residue's…

The paper introduces an operator-level factorial benchmark for molecular MPNNs, finding that message construction (specifically concatenation-based mixing) is the primary determinant of performance, r…

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

The paper introduces GraphIP-Bench, a unified benchmark that demonstrates that stealing Graph Neural Networks (GNNs) is relatively easy, and existing defenses often fail to maintain their integrity af…

The paper introduces trust functions to filter weak supervision labels, enabling near-lossless weak-to-strong generalization by selectively training a strong student using only the most reliable weak…

This paper proposes a scalable topological learning framework for higher-order graph representation by introducing simplified and factored cellular Weisfeiler Leman tests and a novel random walk metho…

The paper uses majorization theory to analyze lattice reduction, showing that local swaps smooth the Gram-Schmidt profile and deriving variational and telescoping identities for the worst-case profile…

GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundar…

The paper introduces and analyzes several novel data appraisal metrics, including the Vendi Score and matrix spectral functions, demonstrating that efficient optimization techniques make these metrics…

The paper introduces a framework for composing deep probabilistic models using five specific factor-graph primitives that guarantee closed-form variational inference, thereby preserving tractability i…

The paper introduces a history-dependent bias to generative protein emulators, significantly improving the exploration of rare and diverse protein states compared to standard emulators.

The paper proposes EPDQ, a tensor-based scheme that efficiently and privately computes exact shortest distance queries on large-scale encrypted graphs by combining specialized indexing and tensor repr…

The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…