A central question in federated learning (FL) is how to design optimization algorithms that minimize the communication cost of training a model over heterogeneous data distributed across many clients. A popular technique for reducing communication is the use of local steps, where clients take multiple optimization steps over local data before communicating with the server (e.g., FedAvg, SCAFFOLD). This contrasts with centralized methods, where clients take one optimization step per communication round (e.g., Minibatch SGD). A recent lower bound on the communication complexity of first-order methods shows that centralized methods are optimal over highly-heterogeneous data, whereas local methods are optimal over purely homogeneous data [Woodworth et al., 2020]. For intermediate heterogeneity levels, no algorithm is known to match the lower bound. In this paper, we propose a multistage optimization scheme that nearly matches the lower bound across all heterogeneity levels. The idea is to first run a local method up to a heterogeneity-induced error floor; next, we switch to a centralized method for the remaining steps. Our analysis may help explain empirically-successful stepsize decay methods in FL [Charles et al., 2020; Reddi et al., 2020]. We demonstrate the scheme's practical utility in image classification tasks.
Abusive language is a massive problem in online social platforms. Existing abusive language detection techniques are particularly ill-suited to comments containing heterogeneous abusive language patterns, i.e., both abusive and non-abusive parts. This is due in part to the lack of datasets that explicitly annotate heterogeneity in abusive language. We tackle this challenge by providing an annotated dataset of abusive language in over 11,000 comments from YouTube. We account for heterogeneity in this dataset by separately annotating both the comment as a whole and the individual sentences that comprise each comment. We then propose an algorithm that uses a supervised attention mechanism to detect and categorize abusive content using multi-task learning. We empirically demonstrate the challenges of using traditional techniques on heterogeneous content and the comparative gains in performance of the proposed approach over state-of-the-art methods.
Fringe groups and organizations have a long history of using euphemisms--ordinary-sounding words with a secret meaning--to conceal what they are discussing. Nowadays, one common use of euphemisms is to evade content moderation policies enforced by social media platforms. Existing tools for enforcing policy automatically rely on keyword searches for words on a "ban list", but these are notoriously imprecise: even when limited to swearwords, they can still cause embarrassing false positives. When a commonly used ordinary word acquires a euphemistic meaning, adding it to a keyword-based ban list is hopeless: consider "pot" (storage container or marijuana?) or "heater" (household appliance or firearm?) The current generation of social media companies instead hire staff to check posts manually, but this is expensive, inhumane, and not much more effective. It is usually apparent to a human moderator that a word is being used euphemistically, but they may not know what the secret meaning is, and therefore whether the message violates policy. Also, when a euphemism is banned, the group that used it need only invent another one, leaving moderators one step behind. This paper will demonstrate unsupervised algorithms that, by analyzing words in their sentence-level context, can both detect words being used euphemistically, and identify the secret meaning of each word. Compared to the existing state of the art, which uses context-free word embeddings, our algorithm for detecting euphemisms achieves 30-400% higher detection accuracies of unlabeled euphemisms in a text corpus. Our algorithm for revealing euphemistic meanings of words is the first of its kind, as far as we are aware. In the arms race between content moderators and policy evaders, our algorithms may help shift the balance in the direction of the moderators.
We consider strongly convex-concave minimax problems in the federated setting, where the communication constraint is the main bottleneck. When clients are arbitrarily heterogeneous, a simple Minibatch Mirror-prox achieves the best performance. As the clients become more homogeneous, using multiple local gradient updates at the clients significantly improves upon Minibatch Mirror-prox by communicating less frequently. Our goal is to design an algorithm that can harness the benefit of similarity in the clients while recovering the Minibatch Mirror-prox performance under arbitrary heterogeneity (up to log factors). We give the first federated minimax optimization algorithm that achieves this goal. The main idea is to combine (i) SCAFFOLD (an algorithm that performs variance reduction across clients for convex optimization) to erase the worst-case dependency on heterogeneity and (ii) Catalyst (a framework for acceleration based on modifying the objective) to accelerate convergence without amplifying client drift. We prove that this algorithm achieves our goal, and include experiments to validate the theory.
Spectral normalization (SN) is a widely-used technique for improving the stability of Generative Adversarial Networks (GANs) by forcing each layer of the discriminator to have unit spectral norm. This approach controls the Lipschitz constant of the discriminator, and is empirically known to improve sample quality in many GAN architectures. However, there is currently little understanding of why SN is so effective. In this work, we show that SN controls two important failure modes of GAN training: exploding and vanishing gradients. Our proofs illustrate a (perhaps unintentional) connection with the successful LeCun initialization technique, proposed over two decades ago to control gradients in the training of deep neural networks. This connection helps to explain why the most popular implementation of SN for GANs requires no hyperparameter tuning, whereas stricter implementations of SN have poor empirical performance out-of-the-box. Unlike LeCun initialization which only controls gradient vanishing at the beginning of training, we show that SN tends to preserve this property throughout training. Finally, building on this theoretical understanding, we propose Bidirectional Spectral Normalization (BSN), a modification of SN inspired by Xavier initialization, a later improvement to LeCun initialization. Theoretically, we show that BSN gives better gradient control than SN. Empirically, we demonstrate that BSN outperforms SN in sample quality on several benchmark datasets, while also exhibiting better training stability.
Limited data access is a substantial barrier to data-driven networking research and development. Although many organizations are motivated to share data, privacy concerns often prevent the sharing of proprietary data, including between teams in the same organization and with outside stakeholders (e.g., researchers, vendors). Many researchers have therefore proposed synthetic data models, most of which have not gained traction because of their narrow scope. In this work, we present DoppelGANger, a synthetic data generation framework based on generative adversarial networks (GANs). DoppelGANger is designed to work on time series datasets with both continuous features (e.g. traffic measurements) and discrete ones (e.g., protocol name). Modeling time series and mixed-type data is known to be difficult; DoppelGANger circumvents these problems through a new conditional architecture that isolates the generation of metadata from time series, but uses metadata to strongly influence time series generation. We demonstrate the efficacy of DoppelGANger on three real-world datasets. We show that DoppelGANger achieves up to 43% better fidelity than baseline models, and captures structural properties of data that baseline methods are unable to learn. Additionally, it gives data holders an easy mechanism for protecting attributes of their data without substantial loss of data utility.
Training disentangled representations with generative adversarial networks (GANs) remains challenging, with leading implementations failing to achieve comparable performance to Variational Autoencoder (VAE)-based methods. After $\beta$-VAE and FactorVAE discovered that regularizing the total correlation of the latent vectors promotes disentanglement, numerous VAE-based methods emerged. Such a discovery has yet to be made for GANs, and reported disentanglement scores of GAN-based methods are significantly inferior to VAE-based methods on benchmark datasets. To this end, we propose a novel regularizer that achieves higher disentanglement scores than state-of-the-art VAE- and GAN-based approaches. The proposed contrastive regularizer is inspired by a natural notion of disentanglement: latent traversal. Latent traversal refers to generating images by varying one latent code while fixing the rest. We turn this intuition into a regularizer by adding a discriminator that detects how the latent codes are coupled together, in paired examples. Numerical experiments show that this approach improves upon competing state-of-the-art approaches on benchmark datasets.
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little diversity, even when trained on diverse datasets. This phenomenon, known as mode collapse, has been the main focus of several recent advances in GANs. Yet there is little understanding of why mode collapse happens and why existing approaches are able to mitigate mode collapse. We propose a principled approach to handling mode collapse, which we call packing. The main idea is to modify the discriminator to make decisions based on multiple samples from the same class, either real or artificially generated. We borrow analysis tools from binary hypothesis testing---in particular the seminal result of Blackwell [Bla53]---to prove a fundamental connection between packing and mode collapse. We show that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process. Numerical experiments on benchmark datasets suggests that packing provides significant improvements in practice as well.
Anonymous messaging platforms, such as Secret and Whisper, have emerged as important social media for sharing one's thoughts without the fear of being judged by friends, family, or the public. Further, such anonymous platforms are crucial in nations with authoritarian governments; the right to free expression and sometimes the personal safety of the author of the message depend on anonymity. Whether for fear of judgment or personal endangerment, it is crucial to keep anonymous the identity of the user who initially posted a sensitive message. In this paper, we consider an adversary who observes a snapshot of the spread of a message at a certain time. Recent advances in rumor source detection shows that the existing messaging protocols are vulnerable against such an adversary. We introduce a novel messaging protocol, which we call adaptive diffusion, and show that it spreads the messages fast and achieves a perfect obfuscation of the source when the underlying contact network is an infinite regular tree: all users with the message are nearly equally likely to have been the origin of the message. Experiments on a sampled Facebook network show that it effectively hides the location of the source even when the graph is finite, irregular and has cycles. We further consider a stronger adversarial model where a subset of colluding users track the reception of messages. We show that the adaptive diffusion provides a strong protection of the anonymity of the source even under this scenario.