Actionable Data Insights for Machine Learning

*= Equal Contributors
Artificial Intelligence (AI) and Machine Learning (ML) have made tremendous progress in the recent decade and have become ubiquitous in almost all application domains. Many recent advancements in the ease-of-use of ML frameworks and the low-code model training automations have further reduced the threshold for ML model building. As ML algorithms and pre-trained models become commodities, curating the appropriate training datasets and model evaluations remain critical challenges. However, these tasks are labor-intensive and require ML practitioners to have bespoke data…Apple Machine Learning Research

PointConvFormer: Revenge of the Point-based Convolution

We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative position, and Transformers which utilize feature-based attention. In PointConvFormer, attention computed from feature difference between points in the neighborhood is used to modify the convolutional weights at each point. Hence, we preserved the invariances from point convolution, whereas attention helps to select relevant points in the neighborhood for…Apple Machine Learning Research

NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion

Novel view synthesis from a single image requires inferring occluded regions of objects and scenes while simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields (NeRF) on local image features, projecting points to the input image plane, and aggregating 2D features to perform volume rendering. However, under severe occlusion, this projection fails to resolve uncertainty, resulting in blurry renderings that lack details. In this work, we propose NerfDiff, which addresses this issue by distilling the knowledge of a 3D-aware…Apple Machine Learning Research

From Robustness to Privacy and Back

*= Equal Contributors
We study the relationship between two desiderata of algorithms in statistical inference and machine learning—differential privacy and robustness to adversarial data corruptions. Their conceptual similarity was first observed by Dwork and Lei (STOC 2009), who observed that private algorithms satisfy robustness, and gave a general method for converting robust algorithms to private ones. However, all general methods for transforming robust algorithms into private ones lead to suboptimal error rates. Our work gives the first black-box transformation that converts any…Apple Machine Learning Research

Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool. In this work, we investigate and use pseudo-labeling for a recently proposed novel setup: joint transcription and translation of speech, which suffers from an absence of sufficient parallel data resources. We show that under such data-deficient circumstances, the unlabeled data can significantly vary in domain from the supervised data, which results in…Apple Machine Learning Research

Generalization on the Unseen, Logic Reasoning and Degree Curriculum

This paper considers the learning of logical (Boolean) functions with focus on the generalization on the unseen (GOTU) setting, a strong case of out-of-distribution generalization. This is motivated by the fact that the rich combinatorial nature of data in certain reasoning tasks (e.g., arithmetic/logic) makes representative data sampling challenging, and learning successfully under GOTU gives a first vignette of an ‘extrapolating’ or ‘reasoning’ learner. We then study how different network architectures trained by (S)GD perform under GOTU and provide both theoretical and experimental evidence…Apple Machine Learning Research

State Spaces Aren’t Enough: Machine Translation Needs Attention

*= Equal Contributors
Structured State Spaces for Sequences (S4) is a recently proposed sequence model with successful applications in various tasks, e.g., vision, language modeling, and audio. Thanks to its mathematical formulation, it compresses its input to a single hidden state and is able to capture long-range dependencies while avoiding the need for an attention mechanism. In this work, we apply S4 to Machine Translation (MT) and evaluate several encoder-decoder variants on WMT’14 and WMT’16. In contrast with the success in language modeling, we find that S4 lags behind the Transformer…Apple Machine Learning Research

Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunities

Virtual assistants are becoming increasingly important speech-driven Information Retrieval platforms that assist users with various tasks. We discuss open problems and challenges with respect to modeling spoken information queries for virtual assistants, and list opportunities where Information Retrieval methods and research can be applied to improve the quality of virtual assistant speech recognition. We discuss how query domain classification, knowledge graphs and user interaction data, and query personalization can be helpful in improving the accurate recognition of spoken information…Apple Machine Learning Research

Self-Supervised Temporal Analysis of Spatiotemporal Data

*=Equal Contributors
There exists a correlation between geospatial activity temporal patterns and type of land use. A novel self-supervised approach is proposed to survey landscape based on activity time series, where time series signal is transformed to frequency domain and compressed into embeddings by a contractive autoencoder, which preserve cyclic temporal patterns observed in time series. The embeddings are input to segmentation neural network for binary classification. Experiments show that the temporal embeddings are effective in classifying residential area and commercial area.Apple Machine Learning Research