Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys

• URL: http://arxiv.org/abs/2606.02860v1
• Date: Mon, 01 Jun 2026 20:22:03 GMT
• Title: Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys
• Abstract summary: Catastrophic forgetting is often framed as a representational problem.<n>We find that a significant portion of apparent forgetting can be attributed to interface drift between internal stages.<n>Results suggest that continual learning may require better mechanisms for indexing and re-accessing latent computations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Catastrophic forgetting is often framed as a representational problem: after sequential training, a model appears to lose the features that supported performance on earlier tasks. We challenge the stronger form of this view. Across controlled continual-learning settings, we find that a significant portion of apparent forgetting can be attributed to interface drift between internal stages rather than permanent erasure of task-relevant computation. We study this phenomenon through a stitched evaluation protocol that combines early computation from a post-update network with late computation from its predecessor, optionally mediated by a compact, task-specific transport key. We describe transport keys at a systems level as compact interface-alignment operators estimated from a small set of paired anchor activations and evaluated through model stitching. On split CIFAR-100 with a ResNet-style network, transport keys recover most of the original Task A performance after sequential training on Task B. On a compact vision transformer, we observe a similar recovery pattern. These results suggest that continual learning may require better mechanisms for indexing and re-accessing latent computations, not only methods that prevent weight change.

Related papers

• DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning [6.097306160389619]
  Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or computationworks.<n>We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, and under-optimized shared representations in the backbone.<n>We propose the Decoupled Representation Dynamic Network (DRDN), which addresses these challenges via two mechanisms.
  arXiv  Detail & Related papers  (2026-07-02T02:57:58Z)
• Task Scarcity and Label Leakage in Relational Transfer Learning [0.0]
  Training relational foundation models requires learning representations that transfer across tasks, yet available supervision is typically limited to a small number of prediction targets per database.<n>This problem causes learned representations to encode task-specific shortcuts that degrade transfer even within the same schema.<n>We introduce a gradient projection method that removes label-predictive directions from representation updates.<n>On RelBench, this improves within-dataset transfer by +0.145 AUROC on average, often recovering near single-task performance.
  arXiv  Detail & Related papers  (2026-03-31T15:55:33Z)
• Learning with Preserving for Continual Multitask Learning [4.847042727427382]
  We introduce Learning with Preserving (LwP), a novel framework that shifts the focus from preserving task outputs to maintaining the shared representation space.<n>LwP not only mitigates catastrophic forgetting but also consistently outperforms state-of-the-art baselines in CMTL tasks.
  arXiv  Detail & Related papers  (2025-11-11T22:23:20Z)
• Continual Learning for Adaptive AI Systems [0.0]
  Cluster-Aware Replay (CAR) is a hybrid continual learning framework that integrates a small, class-balanced replay buffer with a regularization term.<n>CAR better preserves earlier task performance compared to fine-tuning alone.
  arXiv  Detail & Related papers  (2025-10-09T00:44:32Z)
• Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach [87.8330887605381]
  We show how to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. We synthesize a task-specific query with a learnable and lightweight module, which is independent of the pre-trained model. Our method achieves state-of-the-art performance under memory constraints, showcasing its applicability in real-world situations.
  arXiv  Detail & Related papers  (2024-07-09T15:45:04Z)
• Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images [76.47980643420375]
  This paper builds on the hypothesis that there is an inherent data-hungry matter in learning semantic correspondences. We demonstrate a simple machine annotator reliably enriches paired key points via machine supervision. Our models surpass current state-of-the-art models on semantic correspondence learning benchmarks like SPair-71k, PF-PASCAL, and PF-WILLOW.
  arXiv  Detail & Related papers  (2023-11-30T13:22:15Z)
• Exemplar-Free Continual Transformer with Convolutions [12.207329575724772]
  This paper proposes a new exemplar-free approach for class/task incremental learning called ConTraCon. It does not require task-id to be explicitly present during inference and avoids the need for storing previous training instances. Experiments on four benchmark datasets demonstrate that the proposed approach outperforms several competitive approaches.
  arXiv  Detail & Related papers  (2023-08-22T11:17:51Z)
• Adaptive Cross Batch Normalization for Metric Learning [75.91093210956116]
  Metric learning is a fundamental problem in computer vision. We show that it is equally important to ensure that the accumulated embeddings are up to date. In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration.
  arXiv  Detail & Related papers  (2023-03-30T03:22:52Z)
• PRSNet: A Masked Self-Supervised Learning Pedestrian Re-Identification Method [2.0411082897313984]
  This paper designs a pre-task of mask reconstruction to obtain a pre-training model with strong robustness. The training optimization of the network is performed by improving the triplet loss based on the centroid. This method achieves about 5% higher mAP on Marker1501 and CUHK03 data than existing self-supervised learning pedestrian re-identification methods.
  arXiv  Detail & Related papers  (2023-03-11T07:20:32Z)
• Discrete Key-Value Bottleneck [95.61236311369821]
  Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. One powerful approach that has addressed this challenge involves pre-training of large encoders on volumes of readily available data, followed by task-specific tuning. Given a new task, however, updating the weights of these encoders is challenging as a large number of weights needs to be fine-tuned, and as a result, they forget information about the previous tasks. We propose a model architecture to address this issue, building upon a discrete bottleneck containing pairs of separate and learnable key-value codes.
  arXiv  Detail & Related papers  (2022-07-22T17:52:30Z)
• Dense Unsupervised Learning for Video Segmentation [49.46930315961636]
  We present a novel approach to unsupervised learning for video object segmentation (VOS) Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. Our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.
  arXiv  Detail & Related papers  (2021-11-11T15:15:11Z)
• Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
  We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network. Our motivation is that models are expected to understand complex dynamics from different sources. Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
  arXiv  Detail & Related papers  (2020-09-24T15:40:55Z)

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.