# Robustifying Sequential Neural Processes

arXiv: https://arxiv.org/abs/2006.15987 · HTML: https://mlsanity.com/paper/2006.15987/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2020.

## Built on by (most cited first, 15 of 15)

- [NP-Match: When Neural Processes meet Semi-Supervised Learning](https://mlsanity.com/paper/2207.01066/) (2022)
- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Graph Neural Processes for Spatio-Temporal Extrapolation](https://mlsanity.com/paper/2305.18719/) (2023)
- [Neural Processes with Stochastic Attention: Paying more attention to the context dataset](https://mlsanity.com/paper/2204.05449/) (2022)
- [Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation](https://mlsanity.com/paper/2304.01518/) (2023)
- [Evidential Turing Processes](https://mlsanity.com/paper/2106.01216/) (2021)
- [Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future](https://mlsanity.com/paper/2106.04420/) (2021)
- [Social Processes: Self-Supervised Meta-Learning over Conversational Groups for Forecasting Nonverbal Social Cues](https://mlsanity.com/paper/2107.13576/) (2021)
- [Spatially-Aware Transformer for Embodied Agents](https://mlsanity.com/paper/2402.15160/) (2024)
- [Entity Aware Modelling: A Survey](https://mlsanity.com/paper/2302.08406/) (2023)
- [Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes](https://mlsanity.com/paper/2403.16377/) (2024)
- [Bayesian Convolutional Deep Sets with Task-Dependent Stationary Prior](https://mlsanity.com/paper/2210.12363/) (2022)
- [Parallelized Spatiotemporal Binding](https://mlsanity.com/paper/2402.17077/) (2024)
- [NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning](https://mlsanity.com/paper/2301.13569/) (2023)
- [Multi-Task Neural Processes](https://mlsanity.com/paper/2110.14953/) (2021)

## Abstract (arXiv)

When tasks change over time, meta-transfer learning seeks to improve the efficiency of learning a new task via both meta-learning and transfer-learning. While the standard attention has been effective in a variety of settings, we question its effectiveness in improving meta-transfer learning since the tasks being learned are dynamic and the amount of context can be substantially smaller. In this paper, using a recently proposed meta-transfer learning model, Sequential Neural Processes (SNP), we first empirically show that it suffers from a similar underfitting problem observed in the functions inferred by Neural Processes. However, we further demonstrate that unlike the meta-learning setting, the standard attention mechanisms are not effective in meta-transfer setting. To resolve, we propose a new attention mechanism, Recurrent Memory Reconstruction (RMR), and demonstrate that providing an imaginary context that is recurrently updated and reconstructed with interaction is crucial in achieving effective attention for meta-transfer learning. Furthermore, incorporating RMR into SNP, we propose Attentive Sequential Neural Processes-RMR (ASNP-RMR) and demonstrate in various tasks that ASNP-RMR significantly outperforms the baselines.