The Complexity of Learning Sparse Superposed Features with Feedback

• URL: http://arxiv.org/abs/2502.05407v2
• Date: Tue, 11 Feb 2025 06:57:41 GMT
• Title: The Complexity of Learning Sparse Superposed Features with Feedback
• Authors: Akash Kumar,
• Abstract summary: We investigate whether the underlying learned features of a model can be efficiently retrieved through feedback from an agent. We analyze the feedback complexity associated with learning a feature matrix in sparse settings. Our results establish tight bounds when the agent is permitted to construct activations and demonstrate strong upper bounds in sparse scenarios.
• Score: 0.9838799448847586
• License:
• Abstract: The success of deep networks is crucially attributed to their ability to capture latent features within a representation space. In this work, we investigate whether the underlying learned features of a model can be efficiently retrieved through feedback from an agent, such as a large language model (LLM), in the form of relative \textit{triplet comparisons}. These features may represent various constructs, including dictionaries in LLMs or components of a covariance matrix of Mahalanobis distances. We analyze the feedback complexity associated with learning a feature matrix in sparse settings. Our results establish tight bounds when the agent is permitted to construct activations and demonstrate strong upper bounds in sparse scenarios when the agent's feedback is limited to distributional information. We validate our theoretical findings through experiments on two distinct applications: feature recovery from Recursive Feature Machine-trained models and dictionary extraction from sparse autoencoders trained on Large Language Models.

Related papers

• GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning [51.677086019209554]
  We propose a Generalized Structural Sparse to capture powerful relationships across modalities for pair-wise similarity learning. The distance metric delicately encapsulates two formats of diagonal and block-diagonal terms. Experiments on cross-modal and two extra uni-modal retrieval tasks have validated its superiority and flexibility.
  arXiv  Detail & Related papers  (2024-10-20T03:45:50Z)
• Disentangling Dense Embeddings with Sparse Autoencoders [0.0]
  Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models. We show that the resulting sparse representations maintain semantic fidelity while offering interpretability.
  arXiv  Detail & Related papers  (2024-08-01T15:46:22Z)
• Learning to Extract Structured Entities Using Language Models [52.281701191329]
  Recent advances in machine learning have significantly impacted the field of information extraction. We reformulate the task to be entity-centric, enabling the use of diverse metrics. We contribute to the field by introducing Structured Entity Extraction and proposing the Approximate Entity Set OverlaP metric.
  arXiv  Detail & Related papers  (2024-02-06T22:15:09Z)
• Multi-annotator Deep Learning: A Probabilistic Framework for Classification [2.445702550853822]
  Training standard deep neural networks leads to subpar performances in multi-annotator supervised learning settings. We address this issue by presenting a probabilistic training framework named multi-annotator deep learning (MaDL) A modular network architecture enables us to make varying assumptions regarding annotators' performances. Our findings show MaDL's state-of-the-art performance and robustness against many correlated, spamming annotators.
  arXiv  Detail & Related papers  (2023-04-05T16:00:42Z)
• CHALLENGER: Training with Attribution Maps [63.736435657236505]
  We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. In particular, we show that our generic domain-independent approach yields state-of-the-art results in vision, natural language processing and on time series tasks.
  arXiv  Detail & Related papers  (2022-05-30T13:34:46Z)
• Modeling Multi-Granularity Hierarchical Features for Relation Extraction [26.852869800344813]
  We propose a novel method to extract multi-granularity features based solely on the original input sentences. We show that effective structured features can be attained even without external knowledge.
  arXiv  Detail & Related papers  (2022-04-09T09:44:05Z)
• A Framework to Learn with Interpretation [2.3741312212138896]
  We present a novel framework to jointly learn a predictive model and its associated interpretation model. We seek for a small-size dictionary of high level attribute functions that take as inputs the outputs of selected hidden layers. A detailed pipeline to visualize the learnt features is also developed.
  arXiv  Detail & Related papers  (2020-10-19T09:26:28Z)
• A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention [96.77554122595578]
  We introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference. Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost.
  arXiv  Detail & Related papers  (2020-06-22T08:35:58Z)
• A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning [32.59760685342343]
  Probabilistic Latent Variable Models provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. In this work, we propose ConvDMM, a Gaussian state-space model with non-linear emission and transition functions modelled by deep neural networks. When trained on a large scale speech dataset (LibriSpeech), ConvDMM produces features that significantly outperform multiple self-supervised feature extracting methods.
  arXiv  Detail & Related papers  (2020-06-03T21:50:20Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)
• Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction [80.38130122127882]
  We introduce 14 probing tasks targeting linguistic properties relevant to neural relation extraction (RE) We use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets. We find that the bias induced by the architecture and the inclusion of linguistic features are clearly expressed in the probing task performance.
  arXiv  Detail & Related papers  (2020-04-17T09:17:40Z)

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.