Relational Representation Distillation

• URL: http://arxiv.org/abs/2407.12073v5
• Date: Mon, 12 May 2025 18:39:07 GMT
• Title: Relational Representation Distillation
• Authors: Nikolaos Giakoumoglou, Tania Stathaki,
• Abstract summary: Knowledge distillation involves transferring knowledge from large, cumbersome teacher models to more compact student models.<n>Standard approaches fail to capture important structural relationships in the teacher's internal representations.<n>Recent advances have turned to contrastive learning objectives, but these methods impose overly strict constraints through instance-discrimination.<n>Our method employs separate temperature parameters for teacher and student distributions, with sharper student outputs, enabling precise learning of primary relationships while preserving secondary similarities.
• Score: 6.24302896438145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge distillation involves transferring knowledge from large, cumbersome teacher models to more compact student models. The standard approach minimizes the Kullback-Leibler (KL) divergence between the probabilistic outputs of a teacher and student network. However, this approach fails to capture important structural relationships in the teacher's internal representations. Recent advances have turned to contrastive learning objectives, but these methods impose overly strict constraints through instance-discrimination, forcing apart semantically similar samples even when they should maintain similarity. This motivates an alternative objective by which we preserve relative relationships between instances. Our method employs separate temperature parameters for teacher and student distributions, with sharper student outputs, enabling precise learning of primary relationships while preserving secondary similarities. We show theoretical connections between our objective and both InfoNCE loss and KL divergence. Experiments demonstrate that our method significantly outperforms existing knowledge distillation methods across diverse knowledge transfer tasks, achieving better alignment with teacher models, and sometimes even outperforms the teacher network.

Related papers

• Group Relative Knowledge Distillation: Learning from Teacher's Relational Inductive Bias [5.434571018755813]
  Group Relative Knowledge Distillation (GRKD) is a novel framework that distills teacher knowledge by learning the relative ranking among classes.<n>Experiments on classification benchmarks demonstrate GRKD achieves superior generalization compared to existing methods.
  arXiv  Detail & Related papers  (2025-04-29T07:23:22Z)
• Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling [81.00825302340984]
  We introduce Speculative Knowledge Distillation (SKD) to generate high-quality training data on-the-fly. In SKD, the student proposes tokens, and the teacher replaces poorly ranked ones based on its own distribution. We evaluate SKD on various text generation tasks, including translation, summarization, math, and instruction following.
  arXiv  Detail & Related papers  (2024-10-15T06:51:25Z)
• Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching [0.09999629695552192]
  Correlation Matching Knowledge Distillation (CMKD) method combines the Pearson and Spearman correlation coefficients-based KD loss to achieve more efficient and robust distillation from a stronger teacher model. CMKD is simple yet practical, and extensive experiments demonstrate that it can consistently achieve state-of-the-art performance on CIRAR-100 and ImageNet.
  arXiv  Detail & Related papers  (2024-10-09T05:42:47Z)
• Simple Unsupervised Knowledge Distillation With Space Similarity [15.341380611979524]
  Self-supervised learning (SSL) does not readily extend to smaller architectures. We propose a simple objective to capture the lost information due to normalisation. Our proposed loss component, termed textbfspace similarity, motivates each dimension of a student's feature space to be similar to the corresponding dimension of its teacher.
  arXiv  Detail & Related papers  (2024-09-20T22:54:39Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• Relative Difficulty Distillation for Semantic Segmentation [54.76143187709987]
  We propose a pixel-level KD paradigm for semantic segmentation named Relative Difficulty Distillation (RDD) RDD allows the teacher network to provide effective guidance on learning focus without additional optimization goals. Our research showcases that RDD can integrate with existing KD methods to improve their upper performance bound.
  arXiv  Detail & Related papers  (2024-07-04T08:08:25Z)
• Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning [3.1423836318272773]
  Knowledge distillation (KD) improves the performance of efficient and lightweight models. Most existing KD techniques rely on Kullback-Leibler (KL) divergence. We propose a Robustness-Reinforced Knowledge Distillation (R2KD) that leverages correlation distance and network pruning.
  arXiv  Detail & Related papers  (2023-11-23T11:34:48Z)
• Comparative Knowledge Distillation [102.35425896967791]
  Traditional Knowledge Distillation (KD) assumes readily available access to teacher models for frequent inference. We propose Comparative Knowledge Distillation (CKD), which encourages student models to understand the nuanced differences in a teacher model's interpretations of samples. CKD consistently outperforms state of the art data augmentation and KD techniques.
  arXiv  Detail & Related papers  (2023-11-03T21:55:33Z)
• Contrastive Knowledge Amalgamation for Unsupervised Image Classification [2.6392087010521728]
  Contrastive Knowledge Amalgamation (CKA) aims to learn a compact student model to handle the joint objective from multiple teacher models. Contrastive losses intra- and inter- models are designed to widen the distance between representations of different classes. The alignment loss is introduced to minimize the sample-level distribution differences of teacher-student models in the common representation space.
  arXiv  Detail & Related papers  (2023-07-27T11:21:14Z)
• Improved knowledge distillation by utilizing backward pass knowledge in neural networks [17.437510399431606]
  Knowledge distillation (KD) is one of the prominent techniques for model compression. In this work, we generate new auxiliary training samples based on extracting knowledge from the backward pass of the teacher. We show how this technique can be used successfully in applications of natural language processing (NLP) and language understanding.
  arXiv  Detail & Related papers  (2023-01-27T22:07:38Z)
• 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)
• Structural Knowledge Distillation for Object Detection [2.690687471762886]
  We propose a replacement for the pixel-wise independent lp-norm based on the structural similarity (SSIM) Our method adds only little computational overhead, is straightforward to implement and at the same time it significantly outperforms the standard lp-norms.
  arXiv  Detail & Related papers  (2022-11-23T17:06:52Z)
• Knowledge Distillation from A Stronger Teacher [44.11781464210916]
  This paper presents a method dubbed DIST to distill better from a stronger teacher. We empirically find that the discrepancy of predictions between the student and a stronger teacher may tend to be fairly severer. Our method is simple yet practical, and extensive experiments demonstrate that it adapts well to various architectures.
  arXiv  Detail & Related papers  (2022-05-21T08:30:58Z)
• Generalized Knowledge Distillation via Relationship Matching [53.69235109551099]
  Knowledge of a well-trained deep neural network (a.k.a. the "teacher") is valuable for learning similar tasks. Knowledge distillation extracts knowledge from the teacher and integrates it with the target model. Instead of enforcing the teacher to work on the same task as the student, we borrow the knowledge from a teacher trained from a general label space.
  arXiv  Detail & Related papers  (2022-05-04T06:49:47Z)
• DisCo: Effective Knowledge Distillation For Contrastive Learning of Sentence Embeddings [36.37939188680754]
  We propose an enhanced knowledge distillation framework termed Distill-Contrast (DisCo) DisCo transfers the capability of a large sentence embedding model to a small student model on large unlabelled data. We also propose Contrastive Knowledge Distillation (CKD) to enhance the consistencies among teacher model training, KD, and student model finetuning.
  arXiv  Detail & Related papers  (2021-12-10T16:11:23Z)
• How and When Adversarial Robustness Transfers in Knowledge Distillation? [137.11016173468457]
  This paper studies how and when the adversarial robustness can be transferred from a teacher model to a student model in Knowledge distillation (KD) We show that standard KD training fails to preserve adversarial robustness, and we propose KD with input gradient alignment (KDIGA) for remedy. Under certain assumptions, we prove that the student model using our proposed KDIGA can achieve at least the same certified robustness as the teacher model.
  arXiv  Detail & Related papers  (2021-10-22T21:30:53Z)
• KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation [59.061835562314066]
  We introduce a novel task-oriented attention model, termed as KDExplainer, to shed light on the working mechanism underlying the vanilla KD. We also introduce a portable tool, dubbed as virtual attention module (VAM), that can be seamlessly integrated with various deep neural networks (DNNs) to enhance their performance under KD.
  arXiv  Detail & Related papers  (2021-05-10T08:15:26Z)
• Complementary Relation Contrastive Distillation [13.944372633594085]
  We propose a novel knowledge distillation method, namely Complementary Relation Contrastive Distillation (CRCD) We estimate the mutual relation in an anchor-based way and distill the anchor-student relation under the supervision of its corresponding anchor-teacher relation. Experiments on different benchmarks demonstrate the effectiveness of our proposed CRCD.
  arXiv  Detail & Related papers  (2021-03-29T02:43:03Z)
• Wasserstein Contrastive Representation Distillation [114.24609306495456]
  We propose Wasserstein Contrastive Representation Distillation (WCoRD), which leverages both primal and dual forms of Wasserstein distance for knowledge distillation. The dual form is used for global knowledge transfer, yielding a contrastive learning objective that maximizes the lower bound of mutual information between the teacher and the student networks. Experiments demonstrate that the proposed WCoRD method outperforms state-of-the-art approaches on privileged information distillation, model compression and cross-modal transfer.
  arXiv  Detail & Related papers  (2020-12-15T23:43:28Z)
• Multi-head Knowledge Distillation for Model Compression [65.58705111863814]
  We propose a simple-to-implement method using auxiliary classifiers at intermediate layers for matching features. We show that the proposed method outperforms prior relevant approaches presented in the literature.
  arXiv  Detail & Related papers  (2020-12-05T00:49:14Z)
• Knowledge Distillation Thrives on Data Augmentation [65.58705111863814]
  Knowledge distillation (KD) is a general deep neural network training framework that uses a teacher model to guide a student model. Many works have explored the rationale for its success, however, its interplay with data augmentation (DA) has not been well recognized so far. In this paper, we are motivated by an interesting observation in classification: KD loss can benefit from extended training iterations while the cross-entropy loss does not. We show this disparity arises because of data augmentation: KD loss can tap into the extra information from different input views brought by DA.
  arXiv  Detail & Related papers  (2020-12-05T00:32:04Z)
• MixKD: Towards Efficient Distillation of Large-scale Language Models [129.73786264834894]
  We propose MixKD, a data-agnostic distillation framework, to endow the resulting model with stronger generalization ability. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the error and the empirical error. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.
  arXiv  Detail & Related papers  (2020-11-01T18:47:51Z)
• Knowledge Distillation Beyond Model Compression [13.041607703862724]
  Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or ensemble of models (teacher) In this study, we provide an extensive study on nine different KD methods which covers a broad spectrum of approaches to capture and transfer knowledge.
  arXiv  Detail & Related papers  (2020-07-03T19:54:04Z)
• Learning from a Lightweight Teacher for Efficient Knowledge Distillation [14.865673786025525]
  This paper proposes LW-KD, short for lightweight knowledge distillation. It firstly trains a lightweight teacher network on a synthesized simple dataset, with an adjustable class number equal to that of a target dataset. The teacher then generates soft target whereby an enhanced KD loss could guide student learning, which is a combination of KD loss and adversarial loss for making student output indistinguishable from the output of the teacher.
  arXiv  Detail & Related papers  (2020-05-19T01:54:15Z)
• Heterogeneous Knowledge Distillation using Information Flow Modeling [82.83891707250926]
  We propose a novel KD method that works by modeling the information flow through the various layers of the teacher model. The proposed method is capable of overcoming the aforementioned limitations by using an appropriate supervision scheme during the different phases of the training process.
  arXiv  Detail & Related papers  (2020-05-02T06:56:56Z)

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.