Learning to Encode Position for Transformer with Continuous Dynamical Model

• URL: http://arxiv.org/abs/2003.09229v1
• Date: Fri, 13 Mar 2020 00:41:41 GMT
• Title: Learning to Encode Position for Transformer with Continuous Dynamical Model
• Authors: Xuanqing Liu, Hsiang-Fu Yu, Inderjit Dhillon, Cho-Jui Hsieh
• Abstract summary: We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. We model the evolution of encoded results along position index by such a dynamical system.
• Score: 88.69870971415591
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. Unlike RNN and LSTM, which contain inductive bias by loading the input tokens sequentially, non-recurrent models are less sensitive to position. The main reason is that position information among input units is not inherently encoded, i.e., the models are permutation equivalent; this problem justifies why all of the existing models are accompanied by a sinusoidal encoding/embedding layer at the input. However, this solution has clear limitations: the sinusoidal encoding is not flexible enough as it is manually designed and does not contain any learnable parameters, whereas the position embedding restricts the maximum length of input sequences. It is thus desirable to design a new position layer that contains learnable parameters to adjust to different datasets and different architectures. At the same time, we would also like the encodings to extrapolate in accordance with the variable length of inputs. In our proposed solution, we borrow from the recent Neural ODE approach, which may be viewed as a versatile continuous version of a ResNet. This model is capable of modeling many kinds of dynamical systems. We model the evolution of encoded results along position index by such a dynamical system, thereby overcoming the above limitations of existing methods. We evaluate our new position layers on a variety of neural machine translation and language understanding tasks, the experimental results show consistent improvements over the baselines.

Related papers

• Neural Metamorphosis [72.88137795439407]
  This paper introduces a new learning paradigm termed Neural Metamorphosis (NeuMeta), which aims to build self-morphable neural networks. NeuMeta directly learns the continuous weight manifold of neural networks. It sustains full-size performance even at a 75% compression rate.
  arXiv  Detail & Related papers  (2024-10-10T14:49:58Z)
• Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models [6.809572275782338]
  We develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the transformer model. Our framework can be used to understand and mitigate vanishing/exploding gradients, rank collapse, and instability associated with high attention scores.
  arXiv  Detail & Related papers  (2024-03-14T17:59:14Z)
• Neural Functional Transformers [99.98750156515437]
  This paper uses the attention mechanism to define a novel set of permutation equivariant weight-space layers called neural functional Transformers (NFTs) NFTs respect weight-space permutation symmetries while incorporating the advantages of attention, which have exhibited remarkable success across multiple domains. We also leverage NFTs to develop Inr2Array, a novel method for computing permutation invariant representations from the weights of implicit neural representations (INRs)
  arXiv  Detail & Related papers  (2023-05-22T23:38:27Z)
• Toeplitz Neural Network for Sequence Modeling [46.04964190407727]
  We show that a Toeplitz matrix-vector production trick can reduce the space-time complexity of the sequence modeling to log linear. A lightweight sub-network called relative position encoder is proposed to generate relative position coefficients with a fixed budget of parameters. Despite being trained on 512-token sequences, our model can extrapolate input sequence length up to 14K tokens in inference with consistent performance.
  arXiv  Detail & Related papers  (2023-05-08T14:49:01Z)
• Transformer Language Models without Positional Encodings Still Learn Positional Information [45.42248458957122]
  We find that transformer language models without any explicit positional encoding are still competitive with standard models. We conjecture that causal attention enables the model to infer the number of predecessors that each token can attend to, thereby approximating its absolute position.
  arXiv  Detail & Related papers  (2022-03-30T19:37:07Z)
• Structured Reordering for Modeling Latent Alignments in Sequence Transduction [86.94309120789396]
  We present an efficient dynamic programming algorithm performing exact marginal inference of separable permutations. The resulting seq2seq model exhibits better systematic generalization than standard models on synthetic problems and NLP tasks.
  arXiv  Detail & Related papers  (2021-06-06T21:53:54Z)
• Revisiting Simple Neural Probabilistic Language Models [27.957834093475686]
  This paper revisits the neural probabilistic language model (NPLM) ofcitetBengio2003ANP. When scaled up to modern hardware, this model performs much better than expected on word-level language model benchmarks. Inspired by this result, we modify the Transformer by replacing its first self-attention layer with the NPLM's local concatenation layer.
  arXiv  Detail & Related papers  (2021-04-08T02:18:47Z)
• Embedded methods for feature selection in neural networks [0.0]
  Black box models like neural networks negatively affect the interpretability, generalizability, and the training time of these models. I propose two integrated approaches for feature selection that can be incorporated directly into the parameter learning. I benchmarked both the methods against Permutation Feature Importance (PFI) - a general-purpose feature ranking method and a random baseline.
  arXiv  Detail & Related papers  (2020-10-12T16:33:46Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

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.