Sequential Disentanglement by Extracting Static Information From A Single Sequence Element

• URL: http://arxiv.org/abs/2406.18131v1
• Date: Wed, 26 Jun 2024 07:32:47 GMT
• Title: Sequential Disentanglement by Extracting Static Information From A Single Sequence Element
• Authors: Nimrod Berman, Ilan Naiman, Idan Arbiv, Gal Fadlon, Omri Azencot,
• Abstract summary: One of the fundamental representation learning tasks is unsupervised sequential disentanglement. We propose a novel and simple architecture that mitigates information leakage by offering a simple and effective subtraction inductive bias. We show beyond state-of-the-art results on generation and prediction tasks in comparison to several strong baselines.
• Score: 7.631288333466648
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information, existing methods condition the static and dynamic codes on the entire input sequence. Unfortunately, these models often suffer from information leakage, i.e., the dynamic vectors encode both static and dynamic information, or vice versa, leading to a non-disentangled representation. Attempts to alleviate this problem via reducing the dynamic dimension and auxiliary loss terms gain only partial success. Instead, we propose a novel and simple architecture that mitigates information leakage by offering a simple and effective subtraction inductive bias while conditioning on a single sample. Remarkably, the resulting variational framework is simpler in terms of required loss terms, hyperparameters, and data augmentation. We evaluate our method on multiple data-modality benchmarks including general time series, video, and audio, and we show beyond state-of-the-art results on generation and prediction tasks in comparison to several strong baselines.

Related papers

• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• Data-centric Prompt Tuning for Dynamic Graphs [16.454662267579216]
  Dynamic graphs have attracted increasing attention due to their ability to model complex and evolving relationships in real-world scenarios.<n>Traditional approaches typically pre-train models using dynamic link prediction and directly apply the resulting node temporal embeddings to specific downstream tasks.<n>We propose DDGPrompt, a data-centric prompting framework designed to effectively refine pre-trained node embeddings at the input data level.
  arXiv  Detail & Related papers  (2026-01-17T08:03:09Z)
• DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization [2.7194314957925094]
  We introduce DiViD, the first end-to-end video diffusion framework for explicit static-dynamic factorization.<n>DiViD extracts a global static token from the first frame and per-frame dynamic tokens, explicitly removing static content from the motion code.<n>We evaluate DiViD on real-world benchmarks using swap-based accuracy and cross-leakage metrics.
  arXiv  Detail & Related papers  (2025-07-18T14:09:18Z)
• Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization [66.10528870853324]
  Fusing and balancing multi-modal inputs from novel sensors for dense prediction tasks is critically important.<n>One major limitation is the tendency of multi-modal frameworks to over-rely on easily learnable modalities.<n>We propose a plug-and-play regularization term based on functional entropy, which introduces no additional parameters.
  arXiv  Detail & Related papers  (2025-05-10T12:58:15Z)
• Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization [33.13911801301048]
  Deep neural networks degrade in generalization performance under noisy supervision.<n>Existing methods focus on isolating clean subsets or correcting noisy labels.<n>We propose a novel two-stage noisy learning framework that enables instance-level optimization.
  arXiv  Detail & Related papers  (2025-05-01T19:12:58Z)
• Adaptive debiased SGD in high-dimensional GLMs with streaming data [4.704144189806667]
  We introduce a novel approach to online inference in high-dimensional generalized linear models. Our method operates in a single-pass mode, significantly reducing both time and space complexity. We demonstrate that our method, termed the Approximated Debiased Lasso (ADL), not only mitigates the need for the bounded individual probability condition but also significantly improves numerical performance.
  arXiv  Detail & Related papers  (2024-05-28T15:36:48Z)
• TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
  TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
  arXiv  Detail & Related papers  (2024-01-06T06:26:49Z)
• Information theory for data-driven model reduction in physics and biology [0.0]
  We develop a systematic approach based on the information bottleneck to identify the relevant variables. We show that in the limit of high compression, the relevant variables are directly determined by the slowest-decaying eigenfunctions. It provides a firm foundation to construct interpretable deep learning tools that perform model reduction.
  arXiv  Detail & Related papers  (2023-12-11T18:39:05Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs [16.968490007064872]
  Applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. We show theoretically that this removes pointwise mutual information provided by the decoder input, which is compensated for by utilizing the latent space. Compared to uniform dropout on standard text benchmark datasets, our targeted approach increases both sequence performance and the information captured in the latent space.
  arXiv  Detail & Related papers  (2022-09-26T11:21:19Z)
• Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio [17.214062755082065]
  Disentangled sequential autoencoders (DSAEs) represent a class of probabilistic graphical models. We show that the vanilla DSAE suffers from being sensitive to the choice of model architecture and capacity of the dynamic latent variables. We propose TS-DSAE, a two-stage training framework that first learns sequence-level prior distributions.
  arXiv  Detail & Related papers  (2022-05-12T04:11:25Z)
• Contrastively Disentangled Sequential Variational Autoencoder [20.75922928324671]
  We propose a novel sequence representation learning method, named Contrastively Disentangled Sequential Variational Autoencoder (C-DSVAE) We use a novel evidence lower bound which maximizes the mutual information between the input and the latent factors, while penalizes the mutual information between the static and dynamic factors. Our experiments show that C-DSVAE significantly outperforms the previous state-of-the-art methods on multiple metrics.
  arXiv  Detail & Related papers  (2021-10-22T23:00:32Z)
• Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead [88.17413955380262]
  We introduce a novel architecture for early exiting based on the vision transformer architecture. We show that our method works for both classification and regression problems. We also introduce a novel method for integrating audio and visual modalities within early exits in audiovisual data analysis.
  arXiv  Detail & Related papers  (2021-05-19T13:30:34Z)
• Disentangled Recurrent Wasserstein Autoencoder [17.769077848342334]
  recurrent Wasserstein Autoencoder (R-WAE) is a new framework for generative modeling of sequential data. R-WAE disentangles the representation of an input sequence into static and dynamic factors. Our models outperform other baselines with the same settings in terms of disentanglement and unconditional video generation.
  arXiv  Detail & Related papers  (2021-01-19T07:43:25Z)
• Variational Hyper RNN for Sequence Modeling [69.0659591456772]
  We propose a novel probabilistic sequence model that excels at capturing high variability in time series data. Our method uses temporal latent variables to capture information about the underlying data pattern. The efficacy of the proposed method is demonstrated on a range of synthetic and real-world sequential data.
  arXiv  Detail & Related papers  (2020-02-24T19:30:32Z)

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.