LightPath: Lightweight and Scalable Path Representation Learning

• URL: http://arxiv.org/abs/2307.10171v1
• Date: Wed, 19 Jul 2023 17:57:27 GMT
• Title: LightPath: Lightweight and Scalable Path Representation Learning
• Abstract summary: We propose a lightweight and scalable path representation learning framework, termed LightPath. We first propose a sparse auto-encoder that ensures that the framework achieves good scalability with respect to path length. Next, we propose a relational reasoning framework to enable faster training of more robust sparse path encoders.
• Score: 26.916398258535036
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Movement paths are used widely in intelligent transportation and smart city applications. To serve such applications, path representation learning aims to provide compact representations of paths that enable efficient and accurate operations when used for different downstream tasks such as path ranking and travel cost estimation. In many cases, it is attractive that the path representation learning is lightweight and scalable; in resource-limited environments and under green computing limitations, it is essential. Yet, existing path representation learning studies focus on accuracy and pay at most secondary attention to resource consumption and scalability. We propose a lightweight and scalable path representation learning framework, termed LightPath, that aims to reduce resource consumption and achieve scalability without affecting accuracy, thus enabling broader applicability. More specifically, we first propose a sparse auto-encoder that ensures that the framework achieves good scalability with respect to path length. Next, we propose a relational reasoning framework to enable faster training of more robust sparse path encoders. We also propose global-local knowledge distillation to further reduce the size and improve the performance of sparse path encoders. Finally, we report extensive experiments on two real-world datasets to offer insight into the efficiency, scalability, and effectiveness of the proposed framework.

Related papers

• VikPath: A Vision Kansformer Framework for Effective Obstacle Avoidance in Self-Supervised Pathfinding [12.76109113310209]
  We propose a self-supervised pathfinding framework that considers obstacle proximity and path smoothness.<n>$Design$ achieves an average of 3.28% greater obstacle clearance and 87.07% lower latency while maintaining smooth path generation.
  arXiv  Detail & Related papers  (2026-08-24T00:23:57Z)
• Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling [5.567300300236187]
  Ray tracing has become a standard for accurate radio propagation modeling, but suffers from computational complexity.<n>We propose a comprehensive machine-learning-assisted framework that replaces exhaustive path searching with intelligent sampling via Generative Flow Networks.
  arXiv  Detail & Related papers  (2026-03-02T09:37:34Z)
• Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids [21.75404161469649]
  We present a method that has the optimality and completeness properties of any-angle planners while overcoming computational tractability issues.<n>Experiments on real and synthetic environments demonstrate the proposed approach's solution quality and speed.<n>The framework is open-sourced to allow the robotics and planning community to build on our research.
  arXiv  Detail & Related papers  (2026-02-24T18:18:36Z)
• Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories [11.6132604160666]
  We propose a novel framework for learning fixed-dimensional embeddings for short trajectories by leveraging a Transformer encoder.<n>We analyze the influence of Cosine and FFT-based similarity metrics within the contrastive learning paradigm.<n>Our empirical evaluation on the Argoverse 2 dataset demonstrates that embeddings shaped by Cosine similarity objectives yield superior clustering of trajectories.
  arXiv  Detail & Related papers  (2025-06-03T07:53:04Z)
• Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach [32.91982063297922]
  We propose a novel Slow-Fast Tracking paradigm that flexibly adapts to different operational requirements, termed SFTrack.<n>The proposed framework supports two complementary modes, i.e., a high-precision slow tracker for scenarios with sufficient computational resources, and an efficient fast tracker tailored for latency-aware, resource-constrained environments.<n>Our framework first performs graph-based representation learning from high-temporal-resolution event streams, and then integrates the learned graph-structured information into two FlashAttention-based vision backbones.
  arXiv  Detail & Related papers  (2025-05-19T09:37:23Z)
• Soft Reasoning Paths for Knowledge Graph Completion [63.23109723605835]
  Reasoning paths are reliable information in knowledge graph completion (KGC)<n>In real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities.<n>We introduce soft reasoning paths to make the proposed algorithm more stable against missing path circumstances.
  arXiv  Detail & Related papers  (2025-05-06T08:12:48Z)
• Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints [21.152841961098396]
  We introduce Path-Adaptive Matting (PAM), a framework that dynamically adjusts network paths based on image contexts and computational cost constraints. Experiments on five image matting datasets demonstrate that the proposed PAM framework achieves competitive performance across a range of computational cost constraints.
  arXiv  Detail & Related papers  (2025-03-05T06:56:42Z)
• CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing [56.98081258047281]
  Collaborative Inference with Token-lEvel Routing (CITER) is a framework that enables efficient collaboration between small and large language models. We formulate router training as a policy optimization, where the router receives rewards based on both the quality of predictions and the inference costs of generation. Our experiments show that CITER reduces the inference costs while preserving high-quality generation, offering a promising solution for real-time and resource-constrained applications.
  arXiv  Detail & Related papers  (2025-02-04T03:36:44Z)
• Towards Generative Ray Path Sampling for Faster Point-to-Point Ray Tracing [5.723224501252867]
  We propose a Machine Learning-aided Ray Tracing approach to efficiently sample potential ray paths. Our model learns to prioritize potentially valid paths among all possible paths and scales linearly with scene complexity.
  arXiv  Detail & Related papers  (2024-10-31T09:42:03Z)
• LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning [91.95362946266577]
  Path planning is a fundamental scientific problem in robotics and autonomous navigation. Traditional algorithms like A* and its variants are capable of ensuring path validity but suffer from significant computational and memory inefficiencies as the state space grows. We propose a new LLM based route planning method that synergistically combines the precise pathfinding capabilities of A* with the global reasoning capability of LLMs. This hybrid approach aims to enhance pathfinding efficiency in terms of time and space complexity while maintaining the integrity of path validity, especially in large-scale scenarios.
  arXiv  Detail & Related papers  (2024-06-20T01:24:30Z)
• LightTR: A Lightweight Framework for Federated Trajectory Recovery [15.767265437130586]
  We aim to recover a high-sampled trajectory based on the low-sampled trajectory in free space without road network information. We propose a lightweight framework, LightTR, for federated trajectory recovery based on a client-server architecture.
  arXiv  Detail & Related papers  (2024-05-06T12:20:55Z)
• Explainable Trajectory Representation through Dictionary Learning [7.567576186354494]
  Trajectory representation learning on a network enhances our understanding of vehicular traffic patterns. Existing approaches using classic machine learning or deep learning embed trajectories as dense vectors, which lack interpretability. This paper proposes an explainable trajectory representation learning framework through dictionary learning.
  arXiv  Detail & Related papers  (2023-12-13T10:59:54Z)
• Information-Theoretic Odometry Learning [83.36195426897768]
  We propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language.
  arXiv  Detail & Related papers  (2022-03-11T02:37:35Z)
• Lightweight Object-level Topological Semantic Mapping and Long-term Global Localization based on Graph Matching [19.706907816202946]
  We present a novel lightweight object-level mapping and localization method with high accuracy and robustness. We use object-level features with both semantic and geometric information to model landmarks in the environment. Based on the proposed map, the robust localization is achieved by constructing a novel local semantic scene graph descriptor.
  arXiv  Detail & Related papers  (2022-01-16T05:47:07Z)
• Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction [110.61383502442598]
  We introduce a novel neural network framework termed Cross-Modal Message Propagation Network (CMMPNet) CMMPNet is composed of two deep Auto-Encoders for modality-specific representation learning and a tailor-designed Dual Enhancement Module for cross-modal representation refinement. Experiments on three real-world benchmarks demonstrate the effectiveness of our CMMPNet for robust road extraction.
  arXiv  Detail & Related papers  (2021-11-30T04:30:10Z)
• TRAIL: Near-Optimal Imitation Learning with Suboptimal Data [100.83688818427915]
  We present training objectives that use offline datasets to learn a factored transition model. Our theoretical analysis shows that the learned latent action space can boost the sample-efficiency of downstream imitation learning. To learn the latent action space in practice, we propose TRAIL (Transition-Reparametrized Actions for Imitation Learning), an algorithm that learns an energy-based transition model.
  arXiv  Detail & Related papers  (2021-10-27T21:05:00Z)
• Photon-Driven Neural Path Guiding [102.12596782286607]
  We present a novel neural path guiding approach that can reconstruct high-quality sampling distributions for path guiding from a sparse set of samples. We leverage photons traced from light sources as the input for sampling density reconstruction, which is highly effective for challenging scenes with strong global illumination. Our approach achieves significantly better rendering results of testing scenes than previous state-of-the-art path guiding methods.
  arXiv  Detail & Related papers  (2020-10-05T04:54:01Z)
• DrNAS: Dirichlet Neural Architecture Search [88.56953713817545]
  We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet distribution. With recently developed pathwise derivatives, the Dirichlet parameters can be easily optimized with gradient-based generalization. To alleviate the large memory consumption of differentiable NAS, we propose a simple yet effective progressive learning scheme.
  arXiv  Detail & Related papers  (2020-06-18T08:23:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.