Federated learning (FL) is a popular technique to train machine learning (ML) models on decentralized data sources. In order to sustain long-term participation of data owners, it is important to fairly appraise each data source and compensate data owners for their contribution to the training process. The Shapley value (SV) defines a unique payoff scheme that satisfies many desiderata for a data value notion. It has been increasingly used for valuing training data in centralized learning. However, computing the SV requires exhaustively evaluating the model performance on every subset of data sources, which incurs prohibitive communication cost in the federated setting. Besides, the canonical SV ignores the order of data sources during training, which conflicts with the sequential nature of FL. This paper proposes a variant of the SV amenable to FL, which we call the federated Shapley value. The federated SV preserves the desirable properties of the canonical SV while it can be calculated without incurring extra communication cost and is also able to capture the effect of participation order on data value. We conduct a thorough empirical study of the federated SV on a range of tasks, including noisy label detection, adversarial participant detection, and data summarization on different benchmark datasets, and demonstrate that it can reflect the real utility of data sources for FL and has the potential to enhance system robustness, security, and efficiency. We also report and analyze "failure cases" and hope to stimulate future research.
We propose a new test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attain high accuracy on this test, models must possess extensive world knowledge and problem solving ability. We find that while most recent models have near random-chance accuracy, the very largest GPT-3 model improves over random chance by almost 20 percentage points on average. However, on every one of the 57 tasks, the best models still need substantial improvements before they can reach human-level accuracy. Models also have lopsided performance and frequently do not know when they are wrong. Worse, they still have near-random accuracy on some socially important subjects such as morality and law. By comprehensively evaluating the breadth and depth of a model's academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.
Despite achieving tremendous success, existing deep learning models have exposed limitations in compositional generalization, the capability to learn compositional rules and apply them to unseen cases in a systematic manner. To tackle this issue, we propose the Neural-Symbolic Stack Machine (NeSS). It contains a neural network to generate traces, which are then executed by a symbolic stack machine enhanced with sequence manipulation operations. NeSS combines the expressive power of neural sequence models with the recursion supported by the symbolic stack machine. Without training supervision on execution traces, NeSS achieves 100% generalization performance in three domains: the SCAN benchmark of language-driven navigation tasks, the compositional machine translation benchmark, and context-free grammar parsing tasks.
We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to filter out needlessly inflammatory chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete understanding of basic ethical knowledge. Our work shows that progress can be made on machine ethics today, and it provides a steppingstone toward AI that is aligned with human values.
The use of deep learning techniques has achieved significant progress for program synthesis from input-output examples. However, when the program semantics become more complex, it still remains a challenge to synthesize programs consistent with the specification. In this work, we propose SED, a neural program generation framework that incorporates synthesis, execution, and debugging stages. Instead of purely relying on the neural program synthesizer to generate the final program, SED first produces initial programs using the neural program synthesizer component, then utilizes a neural program debugger to iteratively repair the generated programs. The integration of the debugger component enables SED to modify the programs based on the execution results and specification, which resembles the coding process of human programmers. On Karel, a challenging input-output program synthesis benchmark, SED reduces the error rate of the neural program synthesizer itself by at least 7.5%, and outperforms the standard beam search for decoding.
We introduce three new robustness benchmarks consisting of naturally occurring distribution changes in image style, geographic location, camera operation, and more. Using our benchmarks, we take stock of previously proposed hypotheses for out-of-distribution robustness and put them to the test. We find that using larger models and synthetic data augmentation can improve robustness on real-world distribution shifts, contrary to claims in prior work. Motivated by this, we introduce a new data augmentation method which advances the state-of-the-art and outperforms models pretrained with 1000x more labeled data. We find that some methods consistently help with distribution shifts in texture and local image statistics, but these methods do not help with some other distribution shifts like geographic changes. We conclude that future research must study multiple distribution shifts simultaneously.
Causal graph discovery refers to the process of discovering causal relation graphs from purely observational data. Like other statistical data, a causal graph might leak sensitive information about participants in the dataset. In this paper, we present a differentially private causal graph discovery algorithm, Priv-PC, which improves both utility and running time compared to the state-of-the-art. The design of Priv-PC follows a novel paradigm called sieve-and-examine which uses a small amount of privacy budget to filter out "insignificant" queries, and leverages the remaining budget to obtain highly accurate answers for the "significant" queries. We also conducted the first sensitivity analysis for conditional independence tests including conditional Kendall's tau and conditional Spearman's rho. We evaluated Priv-PC on 4 public datasets and compared with the state-of-the-art. The results show that Priv-PC achieves 10.61 to 32.85 times speedup and better utility.
We consider an adversary looking to steal or attack a black-box machine translation (MT) system, either for financial gain or to exploit model errors. We first show that black-box MT systems can be stolen by querying them with monolingual sentences and training models to imitate their outputs. Using simulated experiments, we demonstrate that MT model stealing is possible even when imitation models have different input data or architectures than their victims. Applying these ideas, we train imitation models that reach within 0.6 BLEU of three production MT systems on both high-resource and low-resource language pairs. We then leverage the similarity of our imitation models to transfer adversarial examples to the production systems. We use gradient-based attacks that expose inputs which lead to semantically-incorrect translations, dropped content, and vulgar model outputs. To mitigate these vulnerabilities, we propose a defense that modifies translation outputs in order to misdirect the optimization of imitation models. This defense degrades imitation model BLEU and attack transfer rates at some cost in BLEU and inference speed.
Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribution (OOD) generalization for seven NLP datasets by constructing a new robustness benchmark with realistic distribution shifts. We measure the generalization of previous models including bag-of-words models, ConvNets, and LSTMs, and we show that pretrained Transformers' performance declines are substantially smaller. Pretrained transformers are also more effective at detecting anomalous or OOD examples, while many previous models are frequently worse than chance. We examine which factors affect robustness, finding that larger models are not necessarily more robust, distillation can be harmful, and more diverse pretraining data can enhance robustness. Finally, we show where future work can improve OOD robustness.