Aligning Logits Generatively for Principled Black-Box Knowledge Distillation

• URL: http://arxiv.org/abs/2205.10490v2
• Date: Sat, 30 Mar 2024 08:52:40 GMT
• Title: Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
• Authors: Jing Ma, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li,
• Abstract summary: Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server. We formalize a two-step workflow consisting of deprivatization and distillation. We propose a new method Mapping-Emulation KD (MEKD) that distills a black-box cumbersome model into a lightweight one.
• Score: 49.43567344782207
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server. B2KD faces challenges such as limited Internet exchange and edge-cloud disparity of data distributions. In this paper, we formalize a two-step workflow consisting of deprivatization and distillation, and theoretically provide a new optimization direction from logits to cell boundary different from direct logits alignment. With its guidance, we propose a new method Mapping-Emulation KD (MEKD) that distills a black-box cumbersome model into a lightweight one. Our method does not differentiate between treating soft or hard responses, and consists of: 1) deprivatization: emulating the inverse mapping of the teacher function with a generator, and 2) distillation: aligning low-dimensional logits of the teacher and student models by reducing the distance of high-dimensional image points. For different teacher-student pairs, our method yields inspiring distillation performance on various benchmarks, and outperforms the previous state-of-the-art approaches.

Related papers

• Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation [64.15918654558816]
  Self-distillation (SSD) training strategy is introduced for filtering and weighting teacher representation to distill from task-relevant representations only. Experimental results on real-world affective computing, wearable/biosignal datasets from the UCR Archive, the HAR dataset, and image classification datasets show that the proposed SSD method can outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-19T14:08:56Z)
• Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures [6.231548250160585]
  Multi-Level Decoupled Knowledge Distillation (MLDR-KD) improves student model performance with gains of up to 4.86% on CodeAR-100 and 2.78% on Tiny-ImageNet datasets respectively.
  arXiv  Detail & Related papers  (2025-02-10T06:41:20Z)
• Inverse Bridge Matching Distillation [69.479483488685]
  Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. We propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice. We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks.
  arXiv  Detail & Related papers  (2025-02-03T13:56:03Z)
• Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration [17.27061613884289]
  We propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce dynamic contrastive regularization to perceive the student's learning state. We also propose a distribution mapping module to extract and align the pixel-level category distribution of the teacher and student models.
  arXiv  Detail & Related papers  (2024-12-12T05:01:17Z)
• One Step Diffusion-based Super-Resolution with Time-Aware Distillation [60.262651082672235]
  Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. Recent techniques have been devised to enhance the sampling efficiency of diffusion-based SR models via knowledge distillation. We propose a time-aware diffusion distillation method, named TAD-SR, to accomplish effective and efficient image super-resolution.
  arXiv  Detail & Related papers  (2024-08-14T11:47:22Z)
• Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion [29.297959023968165]
  This paper proposes a progressive distillation method based on masked generation features for KGC task. Specifically, we perform pre-distillation on PLM to obtain high-quality teacher models, and compress the PLM network to obtain multi-grade student models. The experimental results demonstrate that the model in the pre-distillation stage surpasses the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-19T07:34:36Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• Knowledge Distillation Performs Partial Variance Reduction [93.6365393721122]
  Knowledge distillation is a popular approach for enhancing the performance of ''student'' models. The underlying mechanics behind knowledge distillation (KD) are still not fully understood. We show that KD can be interpreted as a novel type of variance reduction mechanism.
  arXiv  Detail & Related papers  (2023-05-27T21:25:55Z)
• DisWOT: Student Architecture Search for Distillation WithOut Training [0.0]
  We explore a novel training-free framework to search for the best student architectures for a given teacher. Our work first empirically show that the optimal model under vanilla training cannot be the winner in distillation. Our experiments on CIFAR, ImageNet and NAS-Bench-201 demonstrate that our technique achieves state-of-the-art results on different search spaces.
  arXiv  Detail & Related papers  (2023-03-28T01:58:45Z)
• EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval [83.79667141681418]
  Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR) We propose a novel distillation approach that leverages the relative geometry among queries and documents learned by the large teacher model. We show that our approach successfully distills from both dual-encoder (DE) and cross-encoder (CE) teacher models to 1/10th size asymmetric students that can retain 95-97% of the teacher performance.
  arXiv  Detail & Related papers  (2023-01-27T22:04:37Z)
• ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval [54.54667085792404]
  We propose a novel distillation method that significantly advances cross-architecture distillation for dual-encoders. Our method 1) introduces a self on-the-fly distillation method that can effectively distill late interaction (i.e., ColBERT) to vanilla dual-encoder, and 2) incorporates a cascade distillation process to further improve the performance with a cross-encoder teacher.
  arXiv  Detail & Related papers  (2022-05-18T18:05:13Z)
• Data-Efficient Ranking Distillation for Image Retrieval [15.88955427198763]
  Recent approaches tackle this issue using knowledge distillation to transfer knowledge from a deeper and heavier architecture to a much smaller network. In this paper we address knowledge distillation for metric learning problems. Unlike previous approaches, our proposed method jointly addresses the following constraints i) limited queries to teacher model, ii) black box teacher model with access to the final output representation, andiii) small fraction of original training data without any ground-truth labels.
  arXiv  Detail & Related papers  (2020-07-10T10:59:16Z)

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.