Machine Learning

This paper introduces a new message-passing operation for coarsened graphs with theoretical guarantees, improving GNN efficiency and accuracy on large datasets.

GRDL: a novel graph classification method boasting 10x speed improvement over competitors, achieved by treating node embeddings as distributions and avoiding global pooling.

GRANOLA: A novel graph-adaptive normalization layer significantly boosts GNN performance by dynamically adjusting node features based on the input graph’s unique structure.

This paper introduces DRODA, a novel method guaranteeing bounded error in gradual domain adaptation by leveraging manifold constraints and adaptive Wasserstein radii.

Gradient-free methods conquer nonconvex nonsmooth stochastic compositional optimization, providing non-asymptotic convergence rates and improved efficiency for real-world applications.

ACS: Automatic Cyclical Scheduling revolutionizes gradient-based discrete sampling by intelligently switching between exploration and exploitation phases to efficiently navigate complex multimodal dis…

Gradient Rewiring (GRE) improves editable GNN training by addressing gradient inconsistencies, preserving training node performance while correcting target node errors.

HEPO, a novel constrained optimization method, consistently surpasses heuristic-trained policies in reinforcement learning by ensuring policy improvement over heuristics, regardless of heuristic quali…

GCPO: a novel on-policy goal-conditioned reinforcement learning framework tackles limitations of existing HER-based methods by effectively addressing multi-goal Markovian and non-Markovian reward prob…

GO4Align: Dynamically aligning multi-task learning to conquer task imbalance with superior efficiency!

A globally Q-linearly converging Gauss-Newton method (AGN) is introduced for overparameterized non-convex low-rank matrix sensing, significantly improving convergence compared to existing gradient des…

Restless multi-armed bandits with global rewards (RMAB-G) are introduced, extending the model to handle non-separable rewards and offering novel index-based and adaptive policies that outperform exist…

GFT: a novel graph foundation model using transferable computation trees as tokens, improving generalization and reducing negative transfer in graph learning.

Train factorized neural network layers efficiently with Geometry-aware training in Tucker format (TDLRT)!

RNNs represent naturalistic objects in WM using chronological subspaces, defying traditional slot models; object features are less orthogonalized in RNNs vs. perceptual space.

Cross-geometry learning using knowledge distillation significantly improves GNN performance by leveraging both Euclidean and hyperbolic geometric properties of graph data.

GeoTDM: First diffusion model generating realistic 3D geometric trajectories, capturing complex spatial interactions and temporal correspondence, significantly improving generation quality.

GENOT: a flexible neural optimal transport framework for single-cell genomics, enabling stochastic map learning with any cost function, handling unbalanced data, and tackling complex (Fused) Gromov-Wa…

Genetic-guided GFlowNets revolutionize sample-efficient molecular optimization by smartly integrating genetic algorithms into GFlowNets training, achieving state-of-the-art performance with substantia…

GGAD: Generative Semi-supervised Graph Anomaly Detection significantly outperforms existing methods by using a novel approach to generate pseudo-anomaly nodes for training, leveraging asymmetric local…