We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed to first fit the training data with clean labels during an "early learning" phase, before eventually memorizing the examples with false labels. We prove that early learning and memorization are fundamental phenomena in high-dimensional classification tasks, even in simple linear models, and give a theoretical explanation in this setting. Motivated by these findings, we develop a new technique for noisy classification tasks, which exploits the progress of the early learning phase. In contrast with existing approaches, which use the model output during early learning to detect the examples with clean labels, and either ignore or attempt to correct the false labels, we take a different route and instead capitalize on early learning via regularization. There are two key elements to our approach. First, we leverage semi-supervised learning techniques to produce target probabilities based on the model outputs. Second, we design a regularization term that steers the model towards these targets, implicitly preventing memorization of the false labels. The resulting framework is shown to provide robustness to noisy annotations on several standard benchmarks and real-world datasets, where it achieves results comparable to the state of the art.

In naturalistic learning problems, a model's input contains a wide range of features, some useful for the task at hand, and others not. Of the useful features, which ones does the model use? Of the task-irrelevant features, which ones does the model represent? Answers to these questions are important for understanding the basis of models' decisions, as well as for building models that learn versatile, adaptable representations useful beyond the original training task. We study these questions using synthetic datasets in which the task-relevance of input features can be controlled directly. We find that when two features redundantly predict the labels, the model preferentially represents one, and its preference reflects what was most linearly decodable from the untrained model. Over training, task-relevant features are enhanced, and task-irrelevant features are partially suppressed. Interestingly, in some cases, an easier, weakly predictive feature can suppress a more strongly predictive, but more difficult one. Additionally, models trained to recognize both easy and hard features learn representations most similar to models that use only the easy feature. Further, easy features lead to more consistent representations across model runs than do hard features. Finally, models have greater representational similarity to an untrained model than to models trained on a different task. Our results highlight the complex processes that determine which features a model represents.

To enable more natural face-to-face interactions, conversational agents need to adapt their behavior to their interlocutors. One key aspect of this is generation of appropriate non-verbal behavior for the agent, for example facial gestures, here defined as facial expressions and head movements. Most existing gesture-generating systems do not utilize multi-modal cues from the interlocutor when synthesizing non-verbal behavior. Those that do, typically use deterministic methods that risk producing repetitive and non-vivid motions. In this paper, we introduce a probabilistic method to synthesize interlocutor-aware facial gestures - represented by highly expressive FLAME parameters - in dyadic conversations. Our contributions are: a) a method for feature extraction from multi-party video and speech recordings, resulting in a representation that allows for independent control and manipulation of expression and speech articulation in a 3D avatar; b) an extension to MoGlow, a recent motion-synthesis method based on normalizing flows, to also take multi-modal signals from the interlocutor as input and subsequently output interlocutor-aware facial gestures; and c) a subjective evaluation assessing the use and relative importance of the input modalities. The results show that the model successfully leverages the input from the interlocutor to generate more appropriate behavior. Videos, data, and code available at: https://jonepatr.github.io/lets_face_it.

We propose a novel learning framework based on neural mean-field dynamics for inference and estimation problems of diffusions on networks. Our new framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities, which renders a delay differential equation with memory integral approximated by learnable time convolution operators, resulting in a highly structured and interpretable RNN. Directly using cascade data, our framework can jointly learn the structure of the diffusion network and the evolution of infection probabilities, which are cornerstone to important downstream applications such as influence maximization. Connections between parameter learning and optimal control are also established. Empirical study shows that our approach is versatile and robust to variations of the underlying diffusion network models, and significantly outperforms existing approaches in accuracy and efficiency on both synthetic and real-world data.

A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms. This is evidenced by their inability to generalize to data distributions that are outside of their restricted training sets, namely larger inputs and unseen data. We study these generalization issues at the level of numerical subroutines that comprise common algorithms like sorting, shortest paths, and minimum spanning trees. First, we observe that transformer-based sequence-to-sequence models can learn subroutines like sorting a list of numbers, but their performance rapidly degrades as the length of lists grows beyond those found in the training set. We demonstrate that this is due to attention weights that lose fidelity with longer sequences, particularly when the input numbers are numerically similar. To address the issue, we propose a learned conditional masking mechanism, which enables the model to strongly generalize far outside of its training range with near-perfect accuracy on a variety of algorithms. Second, to generalize to unseen data, we show that encoding numbers with a binary representation leads to embeddings with rich structure once trained on downstream tasks like addition or multiplication. This allows the embedding to handle missing data by faithfully interpolating numbers not seen during training.

We formulate a general framework for building structural causal models (SCMs) with deep learning components. The proposed approach employs normalising flows and variational inference to enable tractable inference of exogenous noise variables - a crucial step for counterfactual inference that is missing from existing deep causal learning methods. Our framework is validated on a synthetic dataset built on MNIST as well as on a real-world medical dataset of brain MRI scans. Our experimental results indicate that we can successfully train deep SCMs that are capable of all three levels of Pearl's ladder of causation: association, intervention, and counterfactuals, giving rise to a powerful new approach for answering causal questions in imaging applications and beyond. The code for all our experiments is available at https://github.com/biomedia-mira/deepscm.

Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter complexity because of reduced expressiveness of bijective mapping, which renders the models unfeasibly expensive in terms of parameters. We present an alternative parameterization scheme called NanoFlow, which uses a single neural density estimator to model multiple transformation stages. Hence, we propose an efficient parameter decomposition method and the concept of flow indication embedding, which are key missing components that enable density estimation from a single neural network. Experiments performed on audio and image models confirm that our method provides a new parameter-efficient solution for scalable NFs with significant sublinear parameter complexity.

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded.

We introduce the probabilistic auto-encoder (PAE), a generative model with a lower dimensional latent space that is based on an auto-encoder which is interpreted probabilistically after training using a normalizing flow. The PAE is fast and easy to train, achieves small reconstruction errors, high sample quality and good performance in downstream tasks. Compared to a VAE and its common variants, the PAE trains faster, reaches a lower reconstruction error and produces state of the art sample quality without requiring special tuning parameters or training procedures. We further demonstrate that the PAE is a powerful model for performing the downstream tasks of outlier detection and probabilistic image reconstruction: 1) We identify a PAE-based outlier detection metric which achieves state of the art results and outperforms other likelihood based estimators. 2) We perform high dimensional data inpainting and denoising with uncertainty quantification by means of posterior analysis in the PAE latent space. Most generative models are specifically tuned to excel in one or two applications. With the PAE we introduce an easy-to-train, simple, but at the same time powerful model that performs well and reliably in many tasks without requiring special fine-tuning or training procedures. We make all PAE codes publicly available.

Should sequences be modeled autoregressively---one symbol at a time? How much computation is needed to predict the next symbol? While local normalization is cheap, this also limits its power. We point out that some probability distributions over discrete sequences cannot be well-approximated by any autoregressive model whose runtime and parameter size grow polynomially in the sequence length---even though their unnormalized sequence probabilities are efficient to compute exactly. Intuitively, the probability of the next symbol can be expensive to compute or approximate (even via randomized algorithms) when it marginalizes over exponentially many possible futures, which is in general $\mathrm{NP}$-hard. Our result is conditional on the widely believed hypothesis that $\mathrm{NP} \nsubseteq \mathrm{P/poly}$ (without which the polynomial hierarchy would collapse at the second level). This theoretical observation serves as a caution to the viewpoint that pumping up parameter size is a straightforward way to improve autoregressive models (e.g., in language modeling). It also suggests that globally normalized (energy-based) models may sometimes outperform locally normalized (autoregressive) models, as we demonstrate experimentally for language modeling.