From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication

• URL: http://arxiv.org/abs/2310.01211v2
• Date: Wed, 20 Mar 2024 11:33:50 GMT
• Title: From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
• Authors: Irene Cannistraci, Luca Moschella, Marco Fumero, Valentino Maiorca, Emanuele Rodolà,
• Abstract summary: It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases. We introduce a versatile method to directly incorporate a set of invariances into the representations, constructing a product space of invariant components on top of the latent representations. We validate our solution on classification and reconstruction tasks, observing consistent latent similarity and downstream performance improvements in a zero-shot stitching setting.
• Score: 19.336940758147442
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases. From a geometric perspective, identifying the classes of transformations and the related invariances that connect these representations is fundamental to unlocking applications, such as merging, stitching, and reusing different neural modules. However, estimating task-specific transformations a priori can be challenging and expensive due to several factors (e.g., weights initialization, training hyperparameters, or data modality). To this end, we introduce a versatile method to directly incorporate a set of invariances into the representations, constructing a product space of invariant components on top of the latent representations without requiring prior knowledge about the optimal invariance to infuse. We validate our solution on classification and reconstruction tasks, observing consistent latent similarity and downstream performance improvements in a zero-shot stitching setting. The experimental analysis comprises three modalities (vision, text, and graphs), twelve pretrained foundational models, nine benchmarks, and several architectures trained from scratch.

Related papers

• Initialization is Critical to Whether Transformers Fit Composite Functions by Inference or Memorizing [10.206921909332006]
  We investigate the mechanisms of how transformers behave on compositional problems. We discover that the parameter initialization scale plays a critical role in determining whether the model learns inferential solutions. We find that inferential solutions exhibit low complexity bias, which we hypothesize is a key factor enabling them to learn individual mappings for single anchors.
  arXiv  Detail & Related papers  (2024-05-08T20:23:24Z)
• Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars [36.780346257061495]
  Interpretability methods aim to understand the algorithm implemented by a trained model. We take a critical view of methods that exclusively focus on individual parts of the model.
  arXiv  Detail & Related papers  (2023-12-03T15:34:46Z)
• Latent Space Translation via Semantic Alignment [29.2401314068038]
  We show how representations learned from different neural modules can be translated between different pre-trained networks. Our method directly estimates a transformation between two given latent spaces, thereby enabling effective stitching of encoders and decoders without additional training. Notably, we show how it is possible to zero-shot stitch text encoders and vision decoders, or vice-versa, yielding surprisingly good classification performance in this multimodal setting.
  arXiv  Detail & Related papers  (2023-11-01T17:12:00Z)
• In-Context Convergence of Transformers [63.04956160537308]
  We study the learning dynamics of a one-layer transformer with softmax attention trained via gradient descent. For data with imbalanced features, we show that the learning dynamics take a stage-wise convergence process.
  arXiv  Detail & Related papers  (2023-10-08T17:55:33Z)
• Flow Factorized Representation Learning [109.51947536586677]
  We introduce a generative model which specifies a distinct set of latent probability paths that define different input transformations. We show that our model achieves higher likelihoods on standard representation learning benchmarks while simultaneously being closer to approximately equivariant models.
  arXiv  Detail & Related papers  (2023-09-22T20:15:37Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• A Simple Strategy to Provable Invariance via Orbit Mapping [14.127786615513978]
  We propose a method to make network architectures provably invariant with respect to group actions. In a nutshell, we intend to 'undo' any possible transformation before feeding the data into the actual network.
  arXiv  Detail & Related papers  (2022-09-24T03:40:42Z)
• Heterogeneous Target Speech Separation [52.05046029743995]
  We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts. Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts.
  arXiv  Detail & Related papers  (2022-04-07T17:14:20Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)
• 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)

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.