Task Agnostic Architecture for Algorithm Induction via Implicit Composition

• URL: http://arxiv.org/abs/2404.02450v1
• Date: Wed, 3 Apr 2024 04:31:09 GMT
• Title: Task Agnostic Architecture for Algorithm Induction via Implicit Composition
• Authors: Sahil J. Sindhi, Ignas Budvytis,
• Abstract summary: This position paper aims to explore developing such a unified architecture and proposes a theoretical framework of how it could be constructed. Recent Generative AI, especially Transformer-based models, demonstrate potential as an architecture capable of constructing algorithms for a wide range of domains. Our exploration delves into current capabilities and limitations of Transformer-based and other methods in efficient and correct algorithm composition.
• Score: 10.627575117586417
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Different fields in applied machine learning such as computer vision, speech or natural language processing have been building domain-specialised solutions. Currently, we are witnessing an opposing trend towards developing more generalist architectures, driven by Large Language Models and multi-modal foundational models. These architectures are designed to tackle a variety of tasks, including those previously unseen and using inputs across multiple modalities. Taking this trend of generalization to the extreme suggests the possibility of a single deep network architecture capable of solving all tasks. This position paper aims to explore developing such a unified architecture and proposes a theoretical framework of how it could be constructed. Our proposal is based on the following assumptions. Firstly, tasks are solved by following a sequence of instructions, typically implemented in code for conventional computing hardware, which inherently operates sequentially. Second, recent Generative AI, especially Transformer-based models, demonstrate potential as an architecture capable of constructing algorithms for a wide range of domains. For example, GPT-4 shows exceptional capability at in-context learning of novel tasks which is hard to explain in any other way than the ability to compose novel solutions from fragments on previously learnt algorithms. Third, the observation that the main missing component in developing a truly generalised network is an efficient approach for self-consistent input of previously learnt sub-steps of an algorithm and their (implicit) composition during the network's internal forward pass. Our exploration delves into current capabilities and limitations of Transformer-based and other methods in efficient and correct algorithm composition and proposes a Transformer-like architecture as well as a discrete learning framework to overcome these limitations.

Related papers

• Training Neural Networks with Internal State, Unconstrained Connectivity, and Discrete Activations [66.53734987585244]
  True intelligence may require the ability of a machine learning model to manage internal state. We show that we have not yet discovered the most effective algorithms for training such models. We present one attempt to design such a training algorithm, applied to an architecture with binary activations and only a single matrix of weights.
  arXiv  Detail & Related papers  (2023-12-22T01:19:08Z)
• A Generalist Neural Algorithmic Learner [18.425083543441776]
  We build a single graph neural network processor capable of learning to execute a wide range of algorithms. We show that it is possible to effectively learn algorithms in a multi-task manner, so long as we can learn to execute them well in a single-task regime.
  arXiv  Detail & Related papers  (2022-09-22T16:41:33Z)
• Policy Architectures for Compositional Generalization in Control [71.61675703776628]
  We introduce a framework for modeling entity-based compositional structure in tasks. Our policies are flexible and can be trained end-to-end without requiring any action primitives.
  arXiv  Detail & Related papers  (2022-03-10T06:44:24Z)
• Learning Interpretable Models Through Multi-Objective Neural Architecture Search [0.9990687944474739]
  We propose a framework to optimize for both task performance and "introspectability," a surrogate metric for aspects of interpretability. We demonstrate that jointly optimizing for task error and introspectability leads to more disentangled and debuggable architectures that perform within error.
  arXiv  Detail & Related papers  (2021-12-16T05:50:55Z)
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges [50.22269760171131]
  The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. This text is concerned with exposing pre-defined regularities through unified geometric principles. It provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers.
  arXiv  Detail & Related papers  (2021-04-27T21:09:51Z)
• Explainability-aided Domain Generalization for Image Classification [0.0]
  We show that applying methods and architectures from the explainability literature can achieve state-of-the-art performance for the challenging task of domain generalization. We develop a set of novel algorithms including DivCAM, an approach where the network receives guidance during training via gradient based class activation maps to focus on a diverse set of discriminative features. Since these methods offer competitive performance on top of explainability, we argue that the proposed methods can be used as a tool to improve the robustness of deep neural network architectures.
  arXiv  Detail & Related papers  (2021-04-05T02:27:01Z)
• Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond [114.39616146985001]
  In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of Bi-Level Optimization (BLO) Then we construct a value-function-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies.
  arXiv  Detail & Related papers  (2021-01-27T16:20:23Z)
• Automated Search for Resource-Efficient Branched Multi-Task Networks [81.48051635183916]
  We propose a principled approach, rooted in differentiable neural architecture search, to automatically define branching structures in a multi-task neural network. We show that our approach consistently finds high-performing branching structures within limited resource budgets.
  arXiv  Detail & Related papers  (2020-08-24T09:49:19Z)
• Learning to Stop While Learning to Predict [85.7136203122784]
  Many algorithm-inspired deep models are restricted to a fixed-depth'' for all inputs. Similar to algorithms, the optimal depth of a deep architecture may be different for different input instances. In this paper, we tackle this varying depth problem using a steerable architecture. We show that the learned deep model along with the stopping policy improves the performances on a diverse set of tasks.
  arXiv  Detail & Related papers  (2020-06-09T07:22:01Z)

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.