Posted by Shekoofeh Azizi, AI Resident, Google Research In recent years, there has been increasing interest in applying deep learning to ...

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources due to the noise present in the uncurated data. This is partly due to the fact that the prevalent training scheme is trained on coarse-grained setting, in which vectors representing the whole video clips or natural language sentences are used for computing similarity. Such scheme makes training noisy as part of the video clips can be totally not correlated with the other-modality input such as text description. In this paper, we propose a fine-grained multi-modal self-supervised training scheme that computes the similarity between embeddings at finer-scale (such as individual feature map embeddings and embeddings of phrases), and uses attention mechanisms to reduce noisy pairs' weighting in the loss function. We show that with the proposed pre-training scheme, we can train smaller models, with smaller batch-size and much less computational resources to achieve downstream tasks performances comparable to State-Of-The-Art, for tasks including action recognition and text-image retrievals.

Computer scientists from Lancaster University have developed new AI technology that takes autonomous cars a step closer to our roads. Funded by global car manufacturer Ford, the three-year research project provides a step-change in AI car technology by enabling autonomous cars to recognise new and unexpected situations. Around the world, many different automotive brands, computing companies, and research teams, are developing autonomous car technologies and many of these are using a machine learning technique called'Deep Learning'. Deep Learning works by recognising patterns after the computer system has been shown a large number of different training examples. However, a fundamental drawback with Deep Learning algorithms is that they are unable to recognise scenarios that differ significantly from training examples and, unlike humans, they are incapable of exploring, improving and improvising.

How can an end-user provide feedback if a deployed structured prediction model generates incorrect output? Our goal is to allow users to correct errors directly through interaction, without retraining, by giving feedback on the model's output. We create a dynamic memory architecture with a growing memory of feedbacks about errors in the output. Given a new, unseen input, our model can use feedback from a similar, past erroneous state. On a script generation task, we show empirically that the model learns to apply feedback effectively (up to 30 points improvement), while avoiding similar past mistakes after deployment (up to 10 points improvement on an unseen set). This is a first step towards strengthening deployed models, potentially broadening their utility.

Sparsity priors are commonly used in denoising and image reconstruction. For analysis-type priors, a dictionary defines a representation of signals that is likely to be sparse. In most situations, this dictionary is not known, and is to be recovered from pairs of ground-truth signals and measurements, by minimizing the reconstruction error. This defines a hierarchical optimization problem, which can be cast as a bi-level optimization. Yet, this problem is unsolvable, as reconstructions and their derivative wrt the dictionary have no closed-form expression. However, reconstructions can be iteratively computed using the Forward-Backward splitting (FB) algorithm. In this paper, we approximate reconstructions by the output of the aforementioned FB algorithm. Then, we leverage automatic differentiation to evaluate the gradient of this output wrt the dictionary, which we learn with projected gradient descent. Experiments show that our algorithm successfully learns the 1D Total Variation (TV) dictionary from piecewise constant signals. For the same case study, we propose to constrain our search to dictionaries of 0-centered columns, which removes undesired local minima and improves numerical stability.

Our work reveals a structured shortcoming of the existing mainstream self-supervised learning methods. Whereas self-supervised learning frameworks usually take the prevailing perfect instance level invariance hypothesis for granted, we carefully investigate the pitfalls behind. Particularly, we argue that the existing augmentation pipeline for generating multiple positive views naturally introduces out-of-distribution (OOD) samples that undermine the learning of the downstream tasks. Generating diverse positive augmentations on the input does not always pay off in benefiting downstream tasks. To overcome this inherent deficiency, we introduce a lightweight latent variable model UOTA, targeting the view sampling issue for self-supervised learning. UOTA adaptively searches for the most important sampling region to produce views, and provides viable choice for outlier-robust self-supervised learning approaches. Our method directly generalizes to many mainstream self-supervised learning approaches, regardless of the loss's nature contrastive or not. We empirically show UOTA's advantage over the state-of-the-art self-supervised paradigms with evident margin, which well justifies the existence of the OOD sample issue embedded in the existing approaches. Especially, we theoretically prove that the merits of the proposal boil down to guaranteed estimator variance and bias reduction. Code is available: at https://github.com/ssl-codelab/uota.

In this paper, we tackle the inductive semi-supervised learning problem that aims to obtain label predictions for out-of-sample data. The proposed approach, called Optimal Transport Induction (OTI), extends efficiently an optimal transport based transductive algorithm (OTP) to inductive tasks for both binary and multi-class settings. A series of experiments are conducted on several datasets in order to compare the proposed approach with state-of-the-art methods. Experiments demonstrate the effectiveness of our approach. We make our code publicly available.

Self-supervised learning is a powerful way to learn useful representations from natural data. It has also been suggested as one possible means of building visual representation in humans, but the specific objective and algorithm are unknown. Currently, most self-supervised methods encourage the system to learn an invariant representation of different transformations of the same image in contrast to those of other images. However, such transformations are generally non-biologically plausible, and often consist of contrived perceptual schemes such as random cropping and color jittering. In this paper, we attempt to reverse-engineer these augmentations to be more biologically or perceptually plausible while still conferring the same benefits for encouraging robust representation. Critically, we find that random cropping can be substituted by cortical magnification, and saccade-like sampling of the image could also assist the representation learning. The feasibility of these transformations suggests a potential way that biological visual systems could implement self-supervision. Further, they break the widely accepted spatially-uniform processing assumption used in many computer vision algorithms, suggesting a role for spatially-adaptive computation in humans and machines alike. Our code and demo can be found here (Wang, 2021).

Prediction using the ground truth sounds like an oxymoron in machine learning. However, such an unrealistic setting was used in hundreds, if not thousands of papers in the area of finding graph representations. To evaluate the multi-label problem of node classification by using the obtained representations, many works assume in the prediction stage that the number of labels of each test instance is known. In practice such ground truth information is rarely available, but we point out that such an inappropriate setting is now ubiquitous in this research area. We detailedly investigate why the situation occurs. Our analysis indicates that with unrealistic information, the performance is likely over-estimated. To see why suitable predictions were not used, we identify difficulties in applying some multi-label techniques. For the use in future studies, we propose simple and effective settings without using practically unknown information. Finally, we take this chance to conduct a fair and serious comparison of major graph-representation learning methods on multi-label node classification.

Natural Language Interfaces to Databases (NLIDBs), where users pose queries in Natural Language (NL), are crucial for enabling non-experts to gain insights from data. Developing such interfaces, by contrast, is dependent on experts who often code heuristics for mapping NL to SQL. Alternatively, NLIDBs based on machine learning models rely on supervised examples of NL to SQL mappings (NL-SQL pairs) used as training data. Such examples are again procured using experts, which typically involves more than a one-off interaction. Namely, each data domain in which the NLIDB is deployed may have different characteristics and therefore require either dedicated heuristics or domain-specific training examples. To this end, we propose an alternative approach for training machine learning-based NLIDBs, using weak supervision. We use the recently proposed question decomposition representation called QDMR, an intermediate between NL and formal query languages. Recent work has shown that non-experts are generally successful in translating NL to QDMR. We consequently use NL-QDMR pairs, along with the question answers, as supervision for automatically synthesizing SQL queries. The NL questions and synthesized SQL are then used to train NL-to-SQL models, which we test on five benchmark datasets. Extensive experiments show that our solution, requiring zero expert annotations, performs competitively with models trained on expert annotated data.