Results for "graph search"

Extension of convolution to graph domains using adjacency structure.

Choosing step size along gradient direction.

Search algorithm for generation that keeps top-k partial sequences; can improve likelihood but reduce diversity.

Neural networks that operate on graph-structured data by propagating information along edges.

Retrieval based on embedding similarity rather than keyword overlap, capturing paraphrases and related concepts.

Directed acyclic graph encoding causal relationships.

GNN using attention to weight neighbor contributions dynamically.

Directly optimizing control policies.

Optimal pathfinding algorithm.

GNN framework where nodes iteratively exchange and aggregate messages from neighbors.

Graphs containing multiple node or edge types with different semantics.

Structured graph encoding facts as entity–relation–entity triples.

A datastore optimized for similarity search over embeddings, enabling semantic retrieval at scale.

Finding routes from start to goal.

Configuration choices not learned directly (or not typically learned) that govern training or architecture.

Graphical model expressing factorization of a probability distribution.

Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.

Computing collision-free trajectories.

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.

Tracking where data came from and how it was transformed; key for debugging and compliance.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Probabilistic graphical model for structured prediction.

Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.

Number of steps considered in planning.

Compromising AI systems via libraries, models, or datasets.

Agent reasoning about future outcomes.

Distributed agents producing emergent intelligence.

Agents communicate via shared state.

Direction of steepest ascent of a function.

Lowest possible loss.