English
Related papers

Related papers: Transformers Provably Learn Sparse Token Selection…

200 papers

Feature selection is important step in machine learning since it has shown to improve prediction accuracy while depressing the curse of dimensionality of high dimensional data. The neural networks have experienced tremendous success in…

Machine Learning · Computer Science 2021-07-13 Peter Bugata , Peter Drotar

Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure. However, inference of these codes typically relies on an optimization procedure with poor computational…

Machine Learning · Computer Science 2022-09-02 Kion Fallah , Christopher J. Rozell

A core component present in many successful neural network architectures, is an MLP block of two fully connected layers with a non-linear activation in between. An intriguing phenomenon observed empirically, including in transformer…

Machine Learning · Computer Science 2024-06-27 Pranjal Awasthi , Nishanth Dikkala , Pritish Kamath , Raghu Meka

Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state tracking. In particular, a growing body of literature has shown this limitation primarily…

Machine Learning · Computer Science 2026-02-23 M. Reza Ebrahimi , Michaël Defferrard , Sunny Panchal , Roland Memisevic

Transformers use the dense self-attention mechanism which gives a lot of flexibility for long-range connectivity. Over multiple layers of a deep transformer, the number of possible connectivity patterns increases exponentially. However,…

Machine Learning · Computer Science 2023-06-05 Md Shamim Hussain , Mohammed J. Zaki , Dharmashankar Subramanian

Transformers have become a central architecture for graph learning, but their application to graphs requires first choosing a tokenization: a graph-to-token map that determines which structural information is exposed at the input. In this…

Machine Learning · Computer Science 2026-05-22 Maya Bechler-Speicher , Gilad Yehudai , Gil Harari , Clayton Sanford , Amir Globerson , Joan Bruna

We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients. We find that by stacking…

Machine Learning · Computer Science 2020-11-24 Hoang NT , Takanori Maehara , Tsuyoshi Murata

Despite the widespread success of Transformers on NLP tasks, recent works have found that they struggle to model several formal languages when compared to recurrent models. This raises the question of why Transformers perform well in…

Machine Learning · Computer Science 2023-07-11 Satwik Bhattamishra , Arkil Patel , Varun Kanade , Phil Blunsom

Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction. In this paper, we find that most existing Transformers…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Xiang Chen , Hao Li , Mingqiang Li , Jinshan Pan

With the success of language pretraining, it is highly desirable to develop more efficient architectures of good scalability that can exploit the abundant unlabeled data at a lower cost. To improve the efficiency, we examine the…

Machine Learning · Computer Science 2020-06-08 Zihang Dai , Guokun Lai , Yiming Yang , Quoc V. Le

Modular addition tasks serve as a useful test bed for observing empirical phenomena in deep learning, including the phenomenon of \emph{grokking}. Prior work has shown that one-layer transformer architectures learn Fourier Multiplication…

Machine Learning · Computer Science 2025-03-31 Akshay Rangamani

Pre-trained Transformers inherently possess the characteristic of sparse activation, where only a small fraction of the neurons are activated for each token. While sparse activation has been explored through post-training methods, its…

Computation and Language · Computer Science 2024-10-07 Zhengyan Zhang , Chaojun Xiao , Qiujieli Qin , Yankai Lin , Zhiyuan Zeng , Xu Han , Zhiyuan Liu , Ruobing Xie , Maosong Sun , Jie Zhou

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

We draw upon a previously largely untapped literature on human collective intelligence as a source of inspiration for improving deep learning. Implicit in many algorithms that attempt to solve Deep Reinforcement Learning (DRL) tasks is the…

Artificial Intelligence · Computer Science 2019-02-18 Dhaval Adjodah , Dan Calacci , Yan Leng , Peter Krafft , Esteban Moro , Alex Pentland

We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their…

Machine Learning · Computer Science 2017-06-20 Alfred Bourely , John Patrick Boueri , Krzysztof Choromonski

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

Computation and Language · Computer Science 2023-02-23 Mohammad Akbar-Tajari , Sara Rajaee , Mohammad Taher Pilehvar

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

Despite the popularity of deep learning, structure learning for deep models remains a relatively under-explored area. In contrast, structure learning has been studied extensively for probabilistic graphical models (PGMs). In particular, an…

Machine Learning · Computer Science 2018-03-19 Zhourong Chen , Xiaopeng Li , Nevin L. Zhang

Fully-connected layers in deep neural networks (DNN) are often the throughput and power bottleneck during training. This is due to their large size and low data reuse. Pruning dense layers can significantly reduce the size of these…

Machine Learning · Computer Science 2018-02-13 Mihailo Isakov , Michel A. Kinsy

Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this…

Machine Learning · Statistics 2026-02-06 Siquan Li , Yao Tong , Haonan Wang , Tianyang Hu