Controlled Dynamics Attractor Transformer

Cheng Zhang, Minnan Luo, Zesheng Yang, Ming Li, Yong-Jin Liu, Qinghua Zheng
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:157524-157543, 2026.

Abstract

Transformer architectures have dramatically advanced representation learning and inference in deep models through self-attention mechanisms. In parallel, associative memory frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms. However, their continuous-time inference dynamics lack the biological plausibility of classical Continuous Attractor Neural Networks. To bridge this gap, we propose Controlled Dynamics Attractor Transformer (CDAT), which couples a mixture von Mises–Fisher attention energy with a Hopfield refinement energy, while augmenting energy descent with a CANN-inspired excitation–inhibition modulation. CDAT instantiates a topology-constrained dynamical system whose couplings encode relational structure among tokens, thereby linking attractor-style dynamics to modern energy-based attention. We further provide a constructive dissipation analysis to formally establish their controlled inference dynamics. Benefiting from these robust and structured dynamics, CDAT achieves state-of-the-art performance across multiple benchmarks in graph anomaly detection and graph classification.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-zhang26ea, title = {Controlled Dynamics Attractor Transformer}, author = {Zhang, Cheng and Luo, Minnan and Yang, Zesheng and Li, Ming and Liu, Yong-Jin and Zheng, Qinghua}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {157524--157543}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/zhang26ea/zhang26ea.pdf}, url = {https://proceedings.mlr.press/v306/zhang26ea.html}, abstract = {Transformer architectures have dramatically advanced representation learning and inference in deep models through self-attention mechanisms. In parallel, associative memory frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms. However, their continuous-time inference dynamics lack the biological plausibility of classical Continuous Attractor Neural Networks. To bridge this gap, we propose Controlled Dynamics Attractor Transformer (CDAT), which couples a mixture von Mises–Fisher attention energy with a Hopfield refinement energy, while augmenting energy descent with a CANN-inspired excitation–inhibition modulation. CDAT instantiates a topology-constrained dynamical system whose couplings encode relational structure among tokens, thereby linking attractor-style dynamics to modern energy-based attention. We further provide a constructive dissipation analysis to formally establish their controlled inference dynamics. Benefiting from these robust and structured dynamics, CDAT achieves state-of-the-art performance across multiple benchmarks in graph anomaly detection and graph classification.} }
Endnote
%0 Conference Paper %T Controlled Dynamics Attractor Transformer %A Cheng Zhang %A Minnan Luo %A Zesheng Yang %A Ming Li %A Yong-Jin Liu %A Qinghua Zheng %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-zhang26ea %I PMLR %P 157524--157543 %U https://proceedings.mlr.press/v306/zhang26ea.html %V 306 %X Transformer architectures have dramatically advanced representation learning and inference in deep models through self-attention mechanisms. In parallel, associative memory frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms. However, their continuous-time inference dynamics lack the biological plausibility of classical Continuous Attractor Neural Networks. To bridge this gap, we propose Controlled Dynamics Attractor Transformer (CDAT), which couples a mixture von Mises–Fisher attention energy with a Hopfield refinement energy, while augmenting energy descent with a CANN-inspired excitation–inhibition modulation. CDAT instantiates a topology-constrained dynamical system whose couplings encode relational structure among tokens, thereby linking attractor-style dynamics to modern energy-based attention. We further provide a constructive dissipation analysis to formally establish their controlled inference dynamics. Benefiting from these robust and structured dynamics, CDAT achieves state-of-the-art performance across multiple benchmarks in graph anomaly detection and graph classification.
APA
Zhang, C., Luo, M., Yang, Z., Li, M., Liu, Y. & Zheng, Q.. (2026). Controlled Dynamics Attractor Transformer. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:157524-157543 Available from https://proceedings.mlr.press/v306/zhang26ea.html.

Related Material