interaction networks

**Interaction Networks (IN)** are the **pioneering Graph Neural Network architecture designed explicitly for learning physical simulations — predicting how objects interact through forces, collisions, and constraints — by decomposing the simulation into a relation model that computes pairwise forces between objects and an object model that updates each object's state based on the net forces acting on it** — the first demonstration that neural networks can discover Newton's laws implicitly by observing object trajectories. **What Are Interaction Networks?** - **Definition**: An Interaction Network (Battaglia et al., 2016) models a physical scene as a graph where nodes are objects (balls, blocks, springs) and edges are relationships (connected by spring, touching, gravitationally attracted). The network alternates between two learned functions: a relation model that computes the effect of each pairwise interaction, and an object model that integrates all incoming effects to update each object's state (position, velocity). - **Relation Model**: For each edge $(i, j)$ in the interaction graph, the relation model $phi_R$ takes the states of both connected objects and produces an effect vector: $e_{ij} = phi_R(o_i, o_j, r_{ij})$, where $r_{ij}$ encodes the relationship type (spring constant, collision coefficient). This effect vector represents the "force" or "influence" that object $j$ exerts on object $i$. - **Object Model**: For each node $i$, the object model $phi_O$ takes the object's current state and the sum of all incoming effects and produces the updated state: $o_i' = phi_O(o_i, sum_{j} e_{ij})$. This corresponds to Newton's second law — the object's acceleration is determined by the sum of forces acting on it. **Why Interaction Networks Matter** - **Physics Discovery**: Interaction Networks learn to simulate gravity, springs, collisions, and rigid body dynamics purely by watching trajectories — without being given any equations. The relation model implicitly discovers force laws (inverse-square for gravity, Hooke's law for springs) from data, demonstrating that neural networks can rediscover fundamental physics. - **Generalization**: Because the relation and object models are applied uniformly to all edges and nodes, Interaction Networks generalize to scenes with different numbers of objects than seen during training. A model trained on 3-body gravitational systems can simulate 10-body systems without retraining. - **Compositional Physics**: Complex physical scenes involve multiple simultaneous interaction types — gravity, contact, friction, springs. Interaction Networks handle this naturally because each edge can have a different relationship type, and the object model integrates all effects regardless of their source. - **Foundation of GNN Physics**: Interaction Networks established the blueprint for all subsequent neural physics simulators — GNS (Graph Network Simulator), DPI-Net, and learned mesh-based simulators all follow the same pattern of message-passing for forces followed by node updates for state evolution. **Architecture** | Component | Input | Output | Physical Analog | |-----------|-------|--------|------------------| | **Relation Model $phi_R$** | Object pair states + relationship type | Effect vector (force) | Newton's law of gravitation / Hooke's law | | **Aggregation** | All incoming effects per object | Net effect vector | Net force = sum of individual forces | | **Object Model $phi_O$** | Object state + net effect | Updated state (position, velocity) | $F = ma$ → update velocity → update position | **Interaction Networks** are **physics learners** — neural networks that discover how things push, pull, attract, and repel each other by observing the world, implicitly rediscovering the force laws that took humanity centuries to formalize.

Go deeper with CFSGPT

Get AI-powered deep-dives, save terms, and run advanced simulations — free account.

Create Free Account