CoDiNet: Path Distribution Modeling with Consistency and Diversity for Dynamic Routing

• URL: http://arxiv.org/abs/2005.14439v3
• Date: Wed, 26 May 2021 08:21:06 GMT
• Title: CoDiNet: Path Distribution Modeling with Consistency and Diversity for Dynamic Routing
• Authors: Huanyu Wang, Zequn Qin, Songyuan Li, and Xi Li
• Abstract summary: We see dynamic routing networks in a fresh light, formulating a routing method as a mapping from a sample space to a routing space. We propose a novel method, termed CoDiNet, to model the relationship between a sample space and a routing space. Specifically, samples with similar semantics should be mapped into the same area in routing space, while those with dissimilar semantics should be mapped into different areas.
• Score: 19.296118763012146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic routing networks, aimed at finding the best routing paths in the networks, have achieved significant improvements to neural networks in terms of accuracy and efficiency. In this paper, we see dynamic routing networks in a fresh light, formulating a routing method as a mapping from a sample space to a routing space. From the perspective of space mapping, prevalent methods of dynamic routing didn't consider how inference paths would be distributed in the routing space. Thus, we propose a novel method, termed CoDiNet, to model the relationship between a sample space and a routing space by regularizing the distribution of routing paths with the properties of consistency and diversity. Specifically, samples with similar semantics should be mapped into the same area in routing space, while those with dissimilar semantics should be mapped into different areas. Moreover, we design a customizable dynamic routing module, which can strike a balance between accuracy and efficiency. When deployed upon ResNet models, our method achieves higher performance and effectively reduces average computational cost on four widely used datasets.

Related papers

• DynamicRouteGPT: A Real-Time Multi-Vehicle Dynamic Navigation Framework Based on Large Language Models [13.33340860174857]
  Real-time dynamic path planning in complex traffic environments presents challenges, such as varying traffic volumes and signal wait times. Traditional static routing algorithms like Dijkstra and A* compute shortest paths but often fail under dynamic conditions. This paper proposes a novel approach based on causal inference for real-time dynamic path planning, balancing global and local optimality.
  arXiv  Detail & Related papers  (2024-08-26T11:19:58Z)
• Image Captioning via Dynamic Path Customization [100.15412641586525]
  We propose a novel Dynamic Transformer Network (DTNet) for image captioning, which dynamically assigns customized paths to different samples, leading to discriminative yet accurate captions. To validate the effectiveness of our proposed DTNet, we conduct extensive experiments on the MS-COCO dataset and achieve new state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-06-01T07:23:21Z)
• Smart Routing with Precise Link Estimation: DSEE-Based Anypath Routing for Reliable Wireless Networking [6.123324869194196]
  Shortest Anypath routing offers a solution by adapting routing decisions based on real-time link conditions. This paper introduces a novel approach that leverages the Deterministic Sequencing of Exploration and Exploitation (DSEE), a multi-armed bandit algorithm. By coupling DSEE with Anypath routing, this algorithm continuously learns and ensures accurate delivery probability estimation.
  arXiv  Detail & Related papers  (2024-05-16T18:16:56Z)
• Robust Path Selection in Software-defined WANs using Deep Reinforcement Learning [18.586260468459386]
  We propose a data-driven algorithm that does the path selection in the network considering the overhead of route computation and path updates. Our scheme fares well by a factor of 40% with respect to reducing link utilization compared to traditional TE schemes such as ECMP.
  arXiv  Detail & Related papers  (2022-12-21T16:08:47Z)
• Road Network Guided Fine-Grained Urban Traffic Flow Inference [108.64631590347352]
  Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem. We propose a novel Road-Aware Traffic Flow Magnifier (RATFM) that exploits the prior knowledge of road networks. Our method can generate high-quality fine-grained traffic flow maps.
  arXiv  Detail & Related papers  (2021-09-29T07:51:49Z)
• Optimal transport in multilayer networks [68.8204255655161]
  We propose a model where optimal flows on different layers contribute differently to the total cost to be minimized. As an application, we consider transportation networks, where each layer is associated to a different transportation system. We show an example of this result on the real 2-layer network of the city of Bordeaux with bus and tram, where in certain regimes the presence of the tram network significantly unburdens the traffic on the road network.
  arXiv  Detail & Related papers  (2021-06-14T07:33:09Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Learning to Generate Content-Aware Dynamic Detectors [62.74209921174237]
  We introduce a newpective of designing efficient detectors, which is automatically generating sample-adaptive model architecture. We introduce a course-to-fine strat-egy tailored for object detection to guide the learning of dynamic routing. Experiments on MS-COCO dataset demonstrate that CADDet achieves 1.8 higher mAP with 10% fewer FLOPs compared with vanilla routing.
  arXiv  Detail & Related papers  (2020-12-08T08:05:20Z)
• Learning Dynamic Routing for Semantic Segmentation [86.56049245100084]
  This paper studies a conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing. The proposed framework generates data-dependent routes, adapting to the scale distribution of each image. To this end, a differentiable gating function, called soft conditional gate, is proposed to select scale transform paths on the fly.
  arXiv  Detail & Related papers  (2020-03-23T17:22:14Z)

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.