# Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting

arXiv: https://arxiv.org/abs/2603.16985 · HTML: https://mlsanity.com/paper/2603.16985/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Fast Differentiable Sorting and Ranking](https://mlsanity.com/paper/2002.08871/) (2020)
- [Frequency-domain MLPs are More Effective Learners in Time Series Forecasting](https://mlsanity.com/paper/2311.06184/) (2023)
- [Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?](https://mlsanity.com/paper/2207.10551/) (2022)
- [Temporal Relational Ranking for Stock Prediction](https://mlsanity.com/paper/1809.09441/) (2018)
- [Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport](https://mlsanity.com/paper/2106.12950/) (2021)
- [MASTER: Market-Guided Stock Transformer for Stock Price Forecasting](https://mlsanity.com/paper/2312.15235/) (2023)
- [Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers](https://mlsanity.com/paper/2502.07436/) (2025)

## Built on by (most cited first, 1 of 1)

- [DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction](https://mlsanity.com/paper/2610.02866/) (2026)

## Abstract (arXiv)

Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibility. However, many Transformer variants implicitly assume stationarity and stable temporal dynamics -- assumptions routinely violated in financial markets characterized by regime shifts and non-stationarity. Empirically, state-of-the-art time-series Transformers often underperform even vanilla Transformers on financial tasks, while simpler architectures with distinct inductive biases, such as CNNs and RNNs, can achieve stronger performance with substantially lower complexity. At the same time, no single inductive bias dominates across markets or regimes, suggesting that robust financial forecasting requires integrating complementary temporal priors. We propose TIPS (Transformer with Inductive Prior Synthesis), a knowledge distillation framework that synthesizes diverse inductive biases -- causality, locality, and periodicity -- within a unified Transformer. TIPS trains bias-specialized Transformer teachers via attention masking, then distills their knowledge into a single student model with regime-dependent alignment across inductive biases. Across four major equity markets, TIPS achieves state-of-the-art performance, outperforming strong ensemble baselines by 55%, 9%, and 16% in annual return, Sharpe ratio, and Calmar ratio, while requiring only 38% of the inference-time computation. Further analyses show that TIPS generates statistically significant excess returns beyond both vanilla Transformers and its teacher ensembles, and exhibits regime-dependent behavioral alignment with classical architectures during their profitable periods. These results highlight the importance of regime-dependent inductive bias utilization for robust generalization in non-stationary financial time series.