Inductive Biases for Deep Learning of Higher-Level Cognition
Mila（米拉人工智能研究所）；University of Montreal（蒙特利尔大学）
Anirudh Goyal, Yoshua Bengio
备注：
This document contains a review of authors research as part of the requirement of AG's predoctoral exam, an overview of the main contributions of the authors few recent papers (co-authored with several other co-authors) as well as a vision of proposed future research
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopedic list of heuristics). If that hypothesis was correct, we could more easily both understand our own intelligence and build intelligent machines. Just like in physics, the principles themselves would not be sufficient to predict the behavior of complex systems like brains, and substantial computation might be needed to simulate human-like intelligence. This hypothesis would suggest that studying the kind of inductive biases that humans and animals exploit could help both clarify these principles and provide inspiration for AI research and neuroscience theories. Deep learning already exploits several key inductive biases, and this work considers a larger list, focusing on those which concern mostly higher-level and sequential conscious processing. The objective of clarifying these particular principles is that they could potentially help us build AI systems benefiting from humans' abilities in terms of flexible out-of-distribution and systematic generalization, which is currently an area where a large gap exists between state-of-the-art machine learning and human intelligence.
Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically explain the success of contrastive learning on downstream classification tasks prove guarantees depending on properties of {\em augmentations} and the value of {\em contrastive loss} of representations. We demonstrate that such analyses, that ignore {\em inductive biases} of the function class and training algorithm, cannot adequately explain the success of …
With the resurgence of interest in neural networks, representation learning has re-emerged as a central focus in artificial intelligence. Representation learning refers to the discovery of useful encodings of data that make domain-relevant information explicit. Factorial representations identify underlying independent causal factors of variation in data. A factorial representation is compact and faithful, makes the causal factors explicit, and facilitates human interpretation of data. Factorial representations support a variety of applications, including the generation of novel examples, index…
Département d’informatique et de recherche opérationnelle（计算机科学与运筹学系）
In this thesis, we try to build a connection between the two schools by introducing syntactic inductive biases for deep learning models. We propose two families of inductive biases, one for constituency structure and another one for dependency structure. The constituency inductive bias encourages deep learning models to use different units (or neurons) to separately process long-term and short-term information. This separation provides a way for deep learning models to build the latent hierarchical representations from sequential inputs, that a higher-level representation is composed of and ca…
University of Cambridge（剑桥大学）；Intel Labs（英特尔实验室）；Julius-Maximilians-Universität Würzburg（维尔茨堡朱利叶斯-马克西米利安大学）
There is a concerted effort to build domain-general artificial intelligence in the form of universal neural network models with sufficient computational flexibility to solve a wide variety of cognitive tasks but without requiring fine-tuning on individual problem spaces and domains. To do this, models need appropriate priors and inductive biases, such that trained models can generalise to out-of-distribution examples and new problem sets. Here we provide an overview of the hallmarks endowing biological neural networks with the functionality needed for flexible cognition, in order to establish …
University of Cambridge（剑桥大学）；MILA（蒙特利尔学习算法研究所）；McGill University（麦吉尔大学）；Polytechnique Montréal（蒙特利尔综合理工学院）；ServiceNow（ServiceNow公司）
In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence. We investigate the impact of representation learning in artificial agents by developing graph referential games. We empirically show that agents parametrized by graph neural networks develop a more compositional language compared to bag-of-words and sequence models, which allows them to systematically generalize to new combinations of familiar features.
SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；Tencent AI Lab（腾讯AI实验室）
DeepMind（深度思维）；Google Brain（谷歌大脑）；MIT（麻省理工学院）；University of Edinburgh（爱丁堡大学）
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following…
Princeton University（普林斯顿大学）；DeepMind（深度思维）；New York University（纽约大学）；Flatiron Institute（弗莱提荣研究所）；Carnegie Mellon University（卡内基梅隆大学）
We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations. We find the correct known equations, including force laws and Hamiltonians, can be extracted from the neural network. We then apply our method to a non-trivial cosmology example-a detailed dark…
Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks
Neuromatch Academy, Neuromatch, Inc., USA（Neuromatch学院，Neuromatch公司，美国）；McGovern Institute for Brain Research, Massachusetts Institute of Technology (MIT)（麦戈文脑科学研究所，麻省理工学院（MIT））
University of Amsterdam（阿姆斯特丹大学）；Google Brain（谷歌大脑）
Having the right inductive biases can be crucial in many tasks or scenarios where data or computing resources are a limiting factor, or where training data is not perfectly representative of the conditions at test time. However, defining, designing and efficiently adapting inductive biases is not necessarily straightforward. In this paper, we explore the power of knowledge distillation for transferring the effect of inductive biases from one model to another. We consider families of models with different inductive biases, LSTMs vs. Transformers and CNNs vs. MLPs, in the context of tasks and sc…
The ability to discriminate between large and small quantities is a core aspect of basic numerical competence in both humans and animals. In this work, we examine the extent to which the state-of-the-art neural networks designed for vision exhibit this basic ability. Motivated by studies in animal and infant numerical cognition, we use the numerical bisection procedure to test number discrimination in different families of neural architectures. Our results suggest that vision-specific inductive biases are helpful in numerosity discrimination, as models with such biases have lowest test errors …
Inductive Biases in Field-Level Cosmological Inference from Galaxy Catalogs
City University of New York Graduate Center（纽约城市大学研究生中心）；Center for Computational Astrophysics, Flatiron Institute（熨斗研究所计算天体物理学中心）；Columbia University（哥伦比亚大学）；Princeton University（普林斯顿大学）
Delft University of Technology（代尔夫特理工大学）；Gradiant；Bosch Security Systems B.V.（博世安防系统有限公司）；Synergy Sports
The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samples for various key computer vision tasks. To encourage new and creative ideas on incorporating relevant inductive biases to improve the data efficiency of deep learning models, we prohibited the use of pre-trained checkpoints and other transfer learning techniques. The provided baselines are outperformed by a large margin in all five challenges, mainly thanks to extensive data…
Many deep reinforcement learning algorithms contain inductive biases that sculpt the agent's objective and its interface to the environment. These inductive biases can take many forms, including domain knowledge and pretuned hyper-parameters. In general, there is a trade-off between generality and performance when algorithms use such biases. Stronger biases can lead to faster learning, but weaker biases can potentially lead to more general algorithms. This trade-off is important because inductive biases are not free; substantial effort may be required to obtain relevant domain knowledge or to …
ETH Zurich（苏黎世联邦理工学院）；ETH AI Center（苏黎世联邦理工学院人工智能中心）
Classical wisdom suggests that estimators should avoid fitting noise to achieve good generalization. In contrast, modern overparameterized models can yield small test error despite interpolating noise -- a phenomenon often called "benign overfitting" or "harmless interpolation". This paper argues that the degree to which interpolation is harmless hinges upon the strength of an estimator's inductive bias, i.e., how heavily the estimator favors solutions with a certain structure: while strong inductive biases prevent harmless interpolation, weak inductive biases can even require fitting noise to…
NTT Communication Science Laboratories（NTT通信科学实验室）；Osaka University（大阪大学）；RIKEN（理化学研究所）
We propose a neural network-based model for nonlinear dynamics in continuous time that can impose inductive biases on decay rates and/or frequencies. Inductive biases are helpful for training neural networks especially when training data are small. The proposed model is based on the Koopman operator theory, where the decay rate and frequency information is used by restricting the eigenvalues of the Koopman operator that describe linear evolution in a Koopman space. We use neural networks to find an appropriate Koopman space, which are trained by minimizing multi-step forecasting and backcastin…
Domain alignment is currently the most prevalent solution to unsupervised domain-adaptation tasks and are often being presented as minimizers of some theoretical upper-bounds on risk in the target domain. However, further works revealed severe inadequacies between theory and practice: we consolidate this analysis and confirm that imposing domain invariance on features is neither necessary nor sufficient to obtain low target risk. We instead argue that successful deep domain adaptation rely largely on hidden inductive biases found in the common practice, such as model pre-training or design of …
Johns Hopkins University（约翰斯·霍普金斯大学）；University of California, Berkeley（加州大学伯克利分校）；Microsoft Research AI（微软人工智能研究院）；Princeton University（普林斯顿大学）
How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it is unclear which inductive biases can explain observed patterns in language acquisition. To facilitate computational modeling aimed at addressing this question, we introduce a framework for giving particular linguistic inductive biases to a neural network model; such a model can then be used to empirically explore the effects of those inductive biases. This framework disentangles universal inductive biases, which are…
Harvard University（哈佛大学）；Microsoft Research NYC（微软研究院纽约）
Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the inductive biases of self-attention modules. Our focus is to rigorously establish which functions and long-range dependencies self-attention blocks prefer to represent. Our main result shows that bounded-norm Transformer networks "create sparse variables": a single self-attention head can represent a sparse function of the input sequence, with sample complexity sca…
Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply to many real world systems, such as those that don't conserve energy or contain contacts, a common setting for robotics and reinforcement learning. In this paper, we examine the inductive biases that make physics-inspired models successful in practice. We show that, contrary to conventional wisdom, the improved generalization of HNNs is the result of modeling acceleration direc…
University of Oxford（牛津大学）；University of Edinburgh（爱丁堡大学）
We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternative approach: Intermediary Latent Space VAEs(InteL-VAEs). InteL-VAEs use an intermediary set of latent variables to control the stochasticity of the encoding process, before mapping these in turn to the latent representation using a parametric function that encapsulates our desired inductive bias(es). This allows us to impose properties like sparsity or clustering on learned representations, and incorporate human knowl…
The etching process is one of the most important processes in semiconductor manufacturing. We have introduced the state-of-the-art deep learning model to predict the etching profiles. However, the significant problems violating physics have been found through various techniques such as explainable artificial intelligence and representation of prediction uncertainty. To address this problem, this paper presents a novel approach to apply the inductive biases for etching process. We demonstrate that our approach fits the measurement faster than physical simulator while following the physical beha…
Although reinforcement learning has been successfully applied in many domains in recent years, we still lack agents that can systematically generalize. While relational inductive biases that fit a task can improve generalization of RL agents, these biases are commonly hard-coded directly in the agent's neural architecture. In this work, we show that we can incorporate relational inductive biases, encoded in the form of relational graphs, into agents. Based on this insight, we propose Grid-to-Graph (GTG), a mapping from grid structures to relational graphs that carry useful spatial relational i…
Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge computational expense, blackbox learned optimizers often struggle with stability and generalization when applied to tasks unlike those in their meta-training set. In this paper, we use tools from dynamical systems to investigate the inductive biases and stability properties of optimization algorithms, and apply the resulting insights to designing inductive biases for bl…
OnePlanet Research Center（OnePlanet研究中心）；imec-the Netherlands（荷兰微电子研究中心（imec荷兰分部））；Google Research（谷歌研究院）；Donders Institute for Brain, Cognition and Behaviour（唐德斯大脑、认知与行为研究所）；Radboud University（拉德堡德大学）
Normalizing flows have shown great success as general-purpose density estimators. However, many real world applications require the use of domain-specific knowledge, which normalizing flows cannot readily incorporate. We propose embedded-model flows (EMF), which alternate general-purpose transformations with structured layers that embed domain-specific inductive biases. These layers are automatically constructed by converting user-specified differentiable probabilistic models into equivalent bijective transformations. We also introduce gated structured layers, which allow bypassing the parts o…
Graph Inductive Biases in Transformers without Message Passing
McGill University（麦吉尔大学）；University of Oxford（牛津大学）；Massachusetts Institute of Technology（麻省理工学院）；MetaAI（Meta人工智能实验室）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能讲席）；FiveAI（FiveAI公司）；International Laboratory on Learning Systems（国际学习系统实验室）
本文提出 GRIT，通过相对位置编码、节点对注意力和度信息注入，在无消息传递的情况下赋予 Graph Transformer 图归纳偏置，并取得理论表达力与 SOTA 性能。
Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
Qwen Large Model Application Team, Alibaba（阿里巴巴大模型应用团队）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Borrowing from the transformer models that revolutionized the field of natural language processing, self-supervised feature learning for visual tasks has also seen state-of-the-art success using these extremely deep, isotropic networks. However, the typical AI researcher does not have the resources to evaluate, let alone train, a model with several billion parameters and quadratic self-attention activations. To facilitate further research, it is necessary to understand the features of these huge transformer models that can be adequately studied by the typical researcher. One interesting charac…
Characterising the Inductive Biases of Neural Networks on Boolean Data
Department of Theoretical Physics, University of Oxford, UK（理论物理系，牛津大学）；Department of Theoretical Chemistry, University of Oxford, UK（理论化学系，牛津大学）；Green Templeton College, University of Oxford, UK（格林·泰尔顿学院，牛津大学）；Department of Computer Science, University of Oxford, UK（计算机科学系，牛津大学）
From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations. However, since auxiliary losses are minimized only on training data, they suffer from the same generalization gap as regular task losses. Moreover, by adding a term to the loss function, the model optimizes a different objective than the one we care about. In this work we address both problems: first, we take …
The performance of state-of-the-art offline RL methods varies widely over the spectrum of dataset qualities, ranging from far-from-optimal random data to close-to-optimal expert demonstrations. We re-implement these methods to test their reproducibility, and show that when a given method outperforms the others on one end of the spectrum, it never does on the other end. This prevents us from naming a victor across the board. We attribute the asymmetry to the amount of inductive bias injected into the agent to entice it to posit that the behavior underlying the offline dataset is optimal for the…
Current deep learning approaches have shown good in-distribution generalization performance, but struggle with out-of-distribution generalization. This is especially true in the case of tasks involving abstract relations like recognizing rules in sequences, as we find in many intelligence tests. Recent work has explored how forcing relational representations to remain distinct from sensory representations, as it seems to be the case in the brain, can help artificial systems. Building on this work, we further explore and formalize the advantages afforded by 'partitioned' representations of rela…
University of Cambridge（剑桥大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；The Alan Turing Institute（艾伦图灵研究所）
We investigate how to exploit structural similarities of an individual's potential outcomes (POs) under different treatments to obtain better estimates of conditional average treatment effects in finite samples. Especially when it is unknown whether a treatment has an effect at all, it is natural to hypothesize that the POs are similar - yet, some existing strategies for treatment effect estimation employ regularization schemes that implicitly encourage heterogeneity even when it does not exist and fail to fully make use of shared structure. In this paper, we investigate and compare three end-…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
The performance of $β$-Variational-Autoencoders ($β$-VAEs) and their variants on learning semantically meaningful, disentangled representations is unparalleled. On the other hand, there are theoretical arguments suggesting the impossibility of unsupervised disentanglement. In this work, we shed light on the inductive bias responsible for the success of VAE-based architectures. We show that in classical datasets the structure of variance, induced by the generating factors, is conveniently aligned with the latent directions fostered by the VAE objective. This builds the pivotal bias on which the…
