Locality Preserving Markovian Transition for Instance Retrieval

• URL: http://arxiv.org/abs/2506.05196v1
• Date: Thu, 05 Jun 2025 16:07:31 GMT
• Title: Locality Preserving Markovian Transition for Instance Retrieval
• Authors: Jifei Luo, Wenzheng Wu, Hantao Yao, Lu Yu, Changsheng Xu,
• Abstract summary: We introduce the Locality Preserving Markovian Transition (LPMT) framework, which employs a long-term thermodynamic transition process with multiple states for accurate manifold distance measurement.<n>The proposed LPMT first integrates diffusion processes across separate graphs using Bidirectional Collaborative Diffusion (BCD) to establish strong similarity relationships.<n>After, Locality State Embedding (LSE) encodes each instance into a distribution for enhanced local consistency.<n>These distributions are interconnected via the Thermodynamic Markovian Transition (TMT) process, enabling efficient global retrieval while maintaining local effectiveness.
• Score: 59.16243976912006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based re-ranking methods are effective in modeling the data manifolds through similarity propagation in affinity graphs. However, positive signals tend to diminish over several steps away from the source, reducing discriminative power beyond local regions. To address this issue, we introduce the Locality Preserving Markovian Transition (LPMT) framework, which employs a long-term thermodynamic transition process with multiple states for accurate manifold distance measurement. The proposed LPMT first integrates diffusion processes across separate graphs using Bidirectional Collaborative Diffusion (BCD) to establish strong similarity relationships. Afterwards, Locality State Embedding (LSE) encodes each instance into a distribution for enhanced local consistency. These distributions are interconnected via the Thermodynamic Markovian Transition (TMT) process, enabling efficient global retrieval while maintaining local effectiveness. Experimental results across diverse tasks confirm the effectiveness of LPMT for instance retrieval.

Related papers

• Sequential Controlled Langevin Diffusions [80.93988625183485]
  Two popular methods are (1) Sequential Monte Carlo (SMC), where the transport is performed through successive densities via prescribed Markov chains and resampling steps, and (2) recently developed diffusion-based sampling methods, where a learned dynamical transport is used.<n>We present a principled framework for combining SMC with diffusion-based samplers by viewing both methods in continuous time and considering measures on path space.<n>This culminates in the new Sequential Controlled Langevin Diffusion (SCLD) sampling method, which is able to utilize the benefits of both methods and reaches improved performance on multiple benchmark problems, in many cases using only 10% of the training budget of previous diffusion-
  arXiv  Detail & Related papers  (2024-12-10T00:47:10Z)
• Decentralizing Test-time Adaptation under Heterogeneous Data Streams [21.40129321379529]
  Test-Time Adaptation (TTA) has shown promise in addressing distribution shifts between training and testing data.<n>Previous attempts merely stabilize model fine-tuning over time to handle continually changing environments.<n>This paper delves into TTA under heterogeneous data streams, moving beyond current model-centric limitations.
  arXiv  Detail & Related papers  (2024-11-16T12:29:59Z)
• Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting [87.37278888311839]
  Iterative Markovian Fitting (IMF) procedure successfully solves the Schr"odinger Bridge (SB) problem.<n>We show a close connection between IMF and the Iterative Proportional Fitting (IPF) procedure.<n>We refer to this combined approach as the Iterative Proportional Markovian Fitting (IPMF) procedure.
  arXiv  Detail & Related papers  (2024-10-03T15:43:17Z)
• Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment [59.75420353684495]
  Machine learning applications on signals such as computer vision or biomedical data often face challenges due to the variability that exists across hardware devices or session recordings. In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities. We show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings.
  arXiv  Detail & Related papers  (2024-07-19T13:33:38Z)
• Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers [10.210248065533133]
  We introduce a novel approach that trains diffusion path samplers (DPS) to address the transition path sampling problem.<n>We reformulate the problem as an amortized sampling from the transition path distribution by minimizing the log-variance divergence between the path distribution induced by DPS and the transition path distribution.<n>We extensively evaluate our approach, termed TPS-DPS, on a synthetic system, small peptide, and challenging fast-folding proteins, demonstrating that it produces more realistic and diverse transition pathways than existing baselines.
  arXiv  Detail & Related papers  (2024-05-30T11:32:42Z)
• Collaborative Heterogeneous Causal Inference Beyond Meta-analysis [68.4474531911361]
  We propose a collaborative inverse propensity score estimator for causal inference with heterogeneous data. Our method shows significant improvements over the methods based on meta-analysis when heterogeneity increases.
  arXiv  Detail & Related papers  (2024-04-24T09:04:36Z)
• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach [49.97755400231656]
  We show that a new accelerated DDPM sampler achieves accelerated performance for three broad distribution classes not considered before.<n>Our results show an improved dependency on the data dimension $d$ among accelerated DDPM type samplers.
  arXiv  Detail & Related papers  (2024-02-21T16:11:47Z)
• Diffusion Methods for Generating Transition Paths [6.222135766747873]
  In this work, we seek to simulate rare transitions between metastable states using score-based generative models. We develop two novel methods for path generation in this paper: a chain-based approach and a midpoint-based approach. Numerical results of generated transition paths for the M"uller potential and for Alanine dipeptide demonstrate the effectiveness of these approaches in both the data-rich and data-scarce regimes.
  arXiv  Detail & Related papers  (2023-09-19T03:03:03Z)
• Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity [44.2308932471393]
  We show that exchanging model estimates leads to linear convergence speedups in the number of agents. In a low-heterogeneity regime, exchanging model estimates leads to linear convergence speedups in the number of agents.
  arXiv  Detail & Related papers  (2023-02-04T17:53:55Z)
• Decentralized Entropic Optimal Transport for Distributed Distribution Comparison [28.122302344024387]
  We propose a novel decentralized entropic optimal transport (DEOT) method, which provides a communication-efficient and privacy-preserving solution to this problem. In particular, we design a mini-batch randomized block-coordinate descent scheme to optimize the DEOT distance in its dual form. We show that the proposed MRBCD scheme and kernel approximation method also apply to entropic Gromov-Wasserstein distance.
  arXiv  Detail & Related papers  (2023-01-28T02:47:42Z)
• Expert-Guided Symmetry Detection in Markov Decision Processes [0.0]
  We propose a paradigm that aims to detect the presence of some transformations of the state-action space for which the MDP dynamics is invariant. The results show that the model distributional shift is reduced when the dataset is augmented with the data obtained by using the detected symmetries.
  arXiv  Detail & Related papers  (2021-11-19T16:12:30Z)
• Comparing Probability Distributions with Conditional Transport [63.11403041984197]
  We propose conditional transport (CT) as a new divergence and approximate it with the amortized CT (ACT) cost. ACT amortizes the computation of its conditional transport plans and comes with unbiased sample gradients that are straightforward to compute. On a wide variety of benchmark datasets generative modeling, substituting the default statistical distance of an existing generative adversarial network with ACT is shown to consistently improve the performance.
  arXiv  Detail & Related papers  (2020-12-28T05:14:22Z)

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.