Search Results for author:
Found 18 papers, 11 papers with code
StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics.
Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systems
We evaluate these models on spring, pendulum, gravitational, and 3D deformable solid systems to compare the performance in terms of rollout error, conserved quantities such as energy and momentum, and generalizability to unseen system sizes.
Global Counterfactual Explainer for Graph Neural Networks
One way to address this is counterfactual reasoning where the objective is to change the GNN prediction by minimal changes in the input graph.
Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network
Lagrangian and Hamiltonian neural networks (LNNs and HNNs, respectively) encode strong inductive biases that allow them to outperform other models of physical systems significantly.
Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems
Neural networks with physics based inductive biases such as Lagrangian neural networks (LNN), and Hamiltonian neural networks (HNN) learn the dynamics of physical systems by encoding strong inductive biases.
Learning the Dynamics of Particle-based Systems with Lagrangian Graph Neural Networks
Physical systems are commonly represented as a combination of particles, the individual dynamics of which govern the system dynamics.
Lifelong Learning for Neural powered Mixed Integer Programming
In this work, we study the hitherto unexplored paradigm of Lifelong Learning to Branch on Mixed Integer Programs.
Gigs with Guarantees: Achieving Fair Wage for Food Delivery Workers
With the increasing popularity of food delivery platforms, it has become pertinent to look into the working conditions of the 'gig' workers in these platforms, especially providing them fair wages, reasonable working hours, and transparency on work availability.
TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs
There has been a recent surge in learning generative models for graphs.
Task and Model Agnostic Adversarial Attack on Graph Neural Networks
In this work, we study this problem and show that GNNs remain vulnerable even when the downstream task and model are unknown.
A Neural Framework for Learning Subgraph and Graph Similarity Measures
Further, owing to its pair-independent embeddings and theoretical properties, NEUROSED allows approximately 3 orders of magnitude faster retrieval of graphs and subgraphs.
NeuroMLR: Robust & Reliable Route Recommendation on Road Networks
First, our study reveals that a significant portion of the routes recommended by existing methods fail to reach the destination.
Lagrangian Neural Network with Differentiable Symmetries and Relational Inductive Bias
However, these models still suffer from issues such as inability to generalize to arbitrary system sizes, poor interpretability, and most importantly, inability to learn translational and rotational symmetries, which lead to the conservation laws of linear and angular momentum, respectively.
NeuroSED: Learning Subgraph Similarity via Graph Neural Networks
Subgraph edit distance (SED) is one of the most expressive measures of subgraph similarity.
Momentum Conserving Lagrangian Neural Networks
However, these models still suffer from issues such as inability to generalize to arbitrary system sizes, poor interpretability, and most importantly, inability to learn translational and rotational symmetries, which lead to the conservation laws of linear and angular momentum, respectively.
GraphReach: Position-Aware Graph Neural Network using Reachability Estimations
In this paper, we develop GraphReach, a position-aware inductive GNN that captures the global positions of nodes through reachability estimations with respect to a set of anchor nodes.
GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generation
Minimum DFS codes are canonical labels and capture the graph structure precisely along with the label information.
Learning Heuristics over Large Graphs via Deep Reinforcement Learning
Additionally, a case-study on the practical combinatorial problem of Influence Maximization (IM) shows GCOMB is 150 times faster than the specialized IM algorithm IMM with similar quality.
