arXiv subjects

Seong Ho Pahng

Publications and source records attributed to Seong Ho Pahng.

3 recordsLinked to original sources

arXiv2026

DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations

Biological systems can form complex three-dimensional structures through the collective behavior of agents that share a common update rule and operate without central control. How such distributed control gives rise to precise global patterns remains a central question not only in developmental biology but also in distributed robotics, programmable matter, and multi-agent learning. Here, we introduce DiffeoMorph, an end-to-end differentiable framework for learning a morphogenesis protocol that guides a population of agents to morph into a target 3D shape. Each agent updates its position and internal state using an SE(3)-equivariant graph neural network, based on its own internal state and signals received from other agents. To train this system, we introduce a new shape-matching loss based on 3D Zernike polynomials, which compares the predicted and target shapes as continuous spatial distributions, not as discrete point clouds, and is invariant to agent ordering, number of agents, and global orientation. To achieve rotation invariance while preserving reflection sensitivity, we include an alignment step that optimally rotates the predicted Zernike spectrum to match the target before computing the loss. We perform benchmarking to establish the advantages of our shape-matching loss over other standard distance metrics for shape comparison tasks. We then demonstrate that DiffeoMorph can form a range of complex shapes from minimally patterned initial conditions. DiffeoMorph provides a general framework for learning distributed control strategies for morphogenesis, swarm robotics, and programmable self-assembly.

cs.LG↗

arXiv2025

Improving Graph Neural Networks by Learning Continuous Edge Directions

Graph Neural Networks (GNNs) traditionally employ a message-passing mechanism that resembles diffusion over undirected graphs, which often leads to homogenization of node features and reduced discriminative power in tasks such as node classification. Our key insight for addressing this limitation is to assign fuzzy edge directions -- that can vary continuously from node $i$ pointing to node $j$ to vice versa -- to the edges of a graph so that features can preferentially flow in one direction between nodes to enable long-range information transmission across the graph. We also introduce a novel complex-valued Laplacian for directed graphs with fuzzy edges where the real and imaginary parts represent information flow in opposite directions. Using this Laplacian, we propose a general framework, called Continuous Edge Direction (CoED) GNN, for learning on graphs with fuzzy edges and prove its expressivity limits using a generalization of the Weisfeiler-Leman (WL) graph isomorphism test for directed graphs with fuzzy edges. Our architecture aggregates neighbor features scaled by the learned edge directions and processes the aggregated messages from in-neighbors and out-neighbors separately alongside the self-features of the nodes. Since continuous edge directions are differentiable, they can be learned jointly with the GNN weights via gradient-based optimization. CoED GNN is particularly well-suited for graph ensemble data where the graph structure remains fixed but multiple realizations of node features are available, such as in gene regulatory networks, web connectivity graphs, and power grids. We demonstrate through extensive experiments on both synthetic and real graph ensemble datasets that learning continuous edge directions significantly improves performance both for undirected and directed graphs compared with existing methods.

cs.LG↗

arXiv2020

Predicting ground state configuration of energy landscape ensemble using graph neural network

Many scientific problems seek to find the ground state in a rugged energy landscape, a task that becomes prohibitively difficult for large systems. Within a particular class of problems, however, the short-range correlations within energy minima might be independent of system size. Can these correlations be inferred from small problems with known ground states to accelerate the search for the ground states of larger problems? Here, we demonstrate the strategy on Ising spin glasses, where the interaction matrices are drawn from protein contact maps. We use graph neural network to learn the mapping from an interaction matrix $J$ to a ground state configuration, yielding guesses for the set of most probable configurations. Given these guesses, we show that ground state configurations can be searched much faster than in vanilla simulated annealing. For large problems, a model trained on small $J$ matrices predicts a configurations whose energy is much lower than those obtained by simulated annealing, indicating the size generalizability of the strategy.

physics.comp-ph↗