Exploring Pseudo-Token Approaches in Transformer Neural Processes

• URL: http://arxiv.org/abs/2504.14416v1
• Date: Sat, 19 Apr 2025 22:47:59 GMT
• Title: Exploring Pseudo-Token Approaches in Transformer Neural Processes
• Authors: Jose Lara-Rangel, Nanze Chen, Fengzhe Zhang,
• Abstract summary: We introduce the Induced Set Attentive Neural Processes (ISANPs)<n>ISANPs perform competitively with Transformer Neural Processes (TNPs) and often surpass state-of-the-art models in 1D regression, image completion, contextual bandits, and Bayesian optimization.<n>ISANPs offer a tunable balance between performance and computational complexity, which scale well to larger datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural Processes (NPs) have gained attention in meta-learning for their ability to quantify uncertainty, together with their rapid prediction and adaptability. However, traditional NPs are prone to underfitting. Transformer Neural Processes (TNPs) significantly outperform existing NPs, yet their applicability in real-world scenarios is hindered by their quadratic computational complexity relative to both context and target data points. To address this, pseudo-token-based TNPs (PT-TNPs) have emerged as a novel NPs subset that condense context data into latent vectors or pseudo-tokens, reducing computational demands. We introduce the Induced Set Attentive Neural Processes (ISANPs), employing Induced Set Attention and an innovative query phase to improve querying efficiency. Our evaluations show that ISANPs perform competitively with TNPs and often surpass state-of-the-art models in 1D regression, image completion, contextual bandits, and Bayesian optimization. Crucially, ISANPs offer a tunable balance between performance and computational complexity, which scale well to larger datasets where TNPs face limitations.

Related papers

• Dimension Agnostic Neural Processes [17.417747846307996]
  Meta-learning aims to train models that can generalize to new tasks with limited labeled data by extracting shared features across diverse task datasets. We introduce Dimension A Neural Processes(DANP), which transforms input features into a fixed-dimensional space and learns a wider range of features that are generalizable across various tasks. We empirically show that DANP outperforms previous NP variations, showcasing its effectiveness in overcoming the limitations of traditional NP models.
  arXiv  Detail & Related papers  (2025-02-28T02:40:59Z)
• In-Context In-Context Learning with Transformer Neural Processes [50.57807892496024]
  We develop the in-context in-context learning pseudo-token TNP (ICICL-TNP) The ICICL-TNP is capable of conditioning on both sets of datapoints and sets of datasets, enabling it to perform in-context in-context learning. We demonstrate the importance of in-context in-context learning and the effectiveness of the ICICL-TNP in a number of experiments.
  arXiv  Detail & Related papers  (2024-06-19T12:26:36Z)
• Effective Learning with Node Perturbation in Multi-Layer Neural Networks [2.1168858935852013]
  node perturbation (NP) proposes learning by the injection of noise into network activations.<n>NP is highly data inefficient and unstable due to its unguided noise-based search process.<n>We find that a closer alignment with directional derivatives together with input decorrelation at every layer strongly enhances performance of NP learning.
  arXiv  Detail & Related papers  (2023-10-02T08:12:51Z)
• Versatile Neural Processes for Learning Implicit Neural Representations [57.090658265140384]
  We propose Versatile Neural Processes (VNP), which largely increases the capability of approximating functions. Specifically, we introduce a bottleneck encoder that produces fewer and informative context tokens, relieving the high computational cost. We demonstrate the effectiveness of the proposed VNP on a variety of tasks involving 1D, 2D and 3D signals.
  arXiv  Detail & Related papers  (2023-01-21T04:08:46Z)
• Latent Bottlenecked Attentive Neural Processes [71.18817592128207]
  We present Latent Bottlenecked Attentive Neural Processes (LBANPs) LBANPs have a querying computational complexity independent of the number of context datapoints. We show LBANPs achieve results competitive with the state-of-the-art on meta-regression, image completion, and contextual multi-armed bandits.
  arXiv  Detail & Related papers  (2022-11-15T19:21:41Z)
• Sample-Then-Optimize Batch Neural Thompson Sampling [50.800944138278474]
  We introduce two algorithms for black-box optimization based on the Thompson sampling (TS) policy. To choose an input query, we only need to train an NN and then choose the query by maximizing the trained NN. Our algorithms sidestep the need to invert the large parameter matrix yet still preserve the validity of the TS policy.
  arXiv  Detail & Related papers  (2022-10-13T09:01:58Z)
• Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling [26.377099481072992]
  We propose Transformer Neural Processes (TNPs) for uncertainty-aware meta learning. We learn TNPs via an autoregressive likelihood-based objective and instantiate it with a novel transformer-based architecture. We show that TNPs achieve state-of-the-art performance on various benchmark problems.
  arXiv  Detail & Related papers  (2022-07-09T02:28:58Z)
• NP-Match: When Neural Processes meet Semi-Supervised Learning [133.009621275051]
  Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data. In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match.
  arXiv  Detail & Related papers  (2022-07-03T15:24:31Z)
• Message Passing Neural Processes [3.0969191504482247]
  We introduce Message Passing Neural Processes (MPNPs), which explicitly makes use of relational structure within the model. MPNPs thrive at lower sampling rates, on existing benchmarks and newly-proposed CA and Cora-Branched tasks. We report strong generalisation over density-based CA rulesets and significant gains in challenging arbitrary-labelling and few-shot learning setups.
  arXiv  Detail & Related papers  (2020-09-29T09:40:09Z)
• Bootstrapping Neural Processes [114.97111530885093]
  Neural Processes (NPs) implicitly define a broad class of processes with neural networks. NPs still rely on an assumption that uncertainty in processes is modeled by a single latent variable. We propose the Boostrapping Neural Process (BNP), a novel extension of the NP family using the bootstrap.
  arXiv  Detail & Related papers  (2020-08-07T02:23:34Z)

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.