Activation functions can have a significant impact on reducing the topological complexity of input data and therefore improve the performance of the model. Selecting a suitable activation function is an essential step in neural model design. However, the choice of activation function is seldom discussed or explored in Transformer-based language models. Their activation functions are chosen beforehand and then remain fixed from pre-training to fine-tuning. As a result, the inductive biases they imposed on models cannot be adjusted during this long life cycle. Moreover, subsequently developed models (e.g., RoBERTa, BART, and GPT-3) often follow up prior work (e.g., BERT) to use the same activation function without justification. In this paper, we investigate the effectiveness of using Rational Activation Function (RAF), a learnable activation function, in the Transformer architecture. In contrast to conventional, predefined activation functions, RAFs can adaptively learn optimal activation functions during training according to input data. Our experiments show the RAF-based Transformer (RAFT) achieves a lower validation perplexity than a vanilla BERT with the GELU function. We further evaluate RAFT on downstream tasks in low- and full-data settings. Our results show that RAFT outperforms the counterpart model across the majority of tasks and settings. For instance, RAFT outperforms vanilla BERT on the GLUE benchmark by 5.71 points on average in low-data scenario (where 100 training examples are available) and by 2.05 points on SQuAD in full-data setting. Analysis of the shapes of learned RAFs further unveils that they substantially vary between different layers of the pre-trained model and mostly look very different from conventional activation functions. RAFT opens a new research direction for analyzing and interpreting pre-trained models according to the learned activation functions.

Large-scale pretrained language models (LMs) are said to ``lack the ability to connect [their] utterances to the world'' (Bender and Koller, 2020). If so, we would expect LM representations to be unrelated to representations in computer vision models. To investigate this, we present an empirical evaluation across three different LMs (BERT, GPT2, and OPT) and three computer vision models (VMs, including ResNet, SegFormer, and MAE). Our experiments show that LMs converge towards representations that are partially isomorphic to those of VMs, with dispersion, and polysemy both factoring into the alignability of vision and language spaces. We discuss the implications of this finding.

We present a continuous-time probabilistic approach for estimating the chirp signal and its instantaneous frequency function when the true forms of these functions are not accessible. Our model represents these functions by non-linearly cascaded Gaussian processes represented as non-linear stochastic differential equations. The posterior distribution of the functions is then estimated with stochastic filters and smoothers. We compute a (posterior) Cram\'er--Rao lower bound for the Gaussian process model, and derive a theoretical upper bound for the estimation error in the mean squared sense. The experiments show that the proposed method outperforms a number of state-of-the-art methods on a synthetic data. We also show that the method works out-of-the-box for two real-world datasets.

Autonomous vehicles that operate in urban environments shall comply with existing rules and reason about the interactions with other decision-making agents. In this paper, we introduce a decentralized and communication-free interaction-aware motion planner and apply it to Autonomous Surface Vessels (ASVs) in urban canals. We build upon a sampling-based method, namely Model Predictive Path Integral control (MPPI), and employ it to, in each time instance, compute both a collision-free trajectory for the vehicle and a prediction of other agents' trajectories, thus modeling interactions. To improve the method's efficiency in multi-agent scenarios, we introduce a two-stage sample evaluation strategy and define an appropriate cost function to achieve rule compliance. We evaluate this decentralized approach in simulations with multiple vessels in real scenarios extracted from Amsterdam's canals, showing superior performance than a state-of-the-art trajectory optimization framework and robustness when encountering different types of agents.

We propose an efficient algorithm for graph matching based on similarity scores constructed from counting a certain family of weighted trees rooted at each vertex. For two Erd\H{o}s-R\'enyi graphs $\mathcal{G}(n,q)$ whose edges are correlated through a latent vertex correspondence, we show that this algorithm correctly matches all but a vanishing fraction of the vertices with high probability, provided that $nq\to\infty$ and the edge correlation coefficient $\rho$ satisfies $\rho^2>\alpha \approx 0.338$, where $\alpha$ is Otter's tree-counting constant. Moreover, this almost exact matching can be made exact under an extra condition that is information-theoretically necessary. This is the first polynomial-time graph matching algorithm that succeeds at an explicit constant correlation and applies to both sparse and dense graphs. In comparison, previous methods either require $\rho=1-o(1)$ or are restricted to sparse graphs. The crux of the algorithm is a carefully curated family of rooted trees called chandeliers, which allows effective extraction of the graph correlation from the counts of the same tree while suppressing the undesirable correlation between those of different trees.

Word embeddings are an essential instrument in many NLP tasks. Most available resources are trained on general language from Web corpora or Wikipedia dumps. However, word embeddings for domain-specific language are rare, in particular for the social science domain. Therefore, in this work, we describe the creation and evaluation of word embedding models based on 37,604 open-access social science research papers. In the evaluation, we compare domain-specific and general language models for (i) language coverage, (ii) diversity, and (iii) semantic relationships. We found that the created domain-specific model, even with a relatively small vocabulary size, covers a large part of social science concepts, their neighborhoods are diverse in comparison to more general models. Across all relation types, we found a more extensive coverage of semantic relationships.

The adoption of machine learning solutions is rapidly increasing across all parts of society. Cloud service providers such as Amazon Web Services, Microsoft Azure and the Google Cloud Platform aggressively expand their Machine-Learning-as-a-Service offerings. While the widespread adoption of machine learning has huge potential for both research and industry, the large-scale evaluation of possibly sensitive data on untrusted platforms bears inherent data security and privacy risks. Since computation time is expensive, performance is a critical factor for machine learning. However, prevailing security measures proposed in the past years come with a significant performance overhead. We investigate the current state of protected distributed machine learning systems, focusing on deep convolutional neural networks. The most common and best-performing mixed MPC approaches are based on homomorphic encryption, secret sharing, and garbled circuits. They commonly suffer from communication overheads that grow linearly in the depth of the neural network. We present Dash, a fast and distributed private machine learning inference scheme. Dash is based purely on arithmetic garbled circuits. It requires only a single communication round per inference step, regardless of the depth of the neural network, and a very small constant communication volume. Dash thus significantly reduces performance requirements and scales better than previous approaches. In addition, we introduce the concept of LabelTensors. This allows us to efficiently use GPUs while using garbled circuits, which further reduces the runtime. Dash offers security against a malicious attacker and is up to 140 times faster than previous arithmetic garbling schemes.

Adversarial imitation learning has become a widely used imitation learning framework. The discriminator is often trained by taking expert demonstrations and policy trajectories as examples respectively from two categories (positive vs. negative) and the policy is then expected to produce trajectories that are indistinguishable from the expert demonstrations. But in the real world, the collected expert demonstrations are more likely to be imperfect, where only an unknown fraction of the demonstrations are optimal. Instead of treating imperfect expert demonstrations as absolutely positive or negative, we investigate unlabeled imperfect expert demonstrations as they are. A positive-unlabeled adversarial imitation learning algorithm is developed to dynamically sample expert demonstrations that can well match the trajectories from the constantly optimized agent policy. The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations. Theoretical analysis shows that our method learns from the imperfect demonstrations via a self-paced way. Experimental results on MuJoCo and RoboSuite platforms demonstrate the effectiveness of our method from different aspects.

State-of-the-art language generation models can degenerate when applied to open-ended generation problems such as text completion, story generation, or dialog modeling. This degeneration usually shows up in the form of incoherence, lack of vocabulary diversity, and self-repetition or copying from the context. In this paper, we postulate that ``human-like'' generations usually lie in a narrow and nearly flat entropy band, and violation of these entropy bounds correlates with degenerate behavior. Our experiments show that this stable narrow entropy zone exists across models, tasks, and domains and confirm the hypothesis that violations of this zone correlate with degeneration. We then use this insight to propose an entropy-aware decoding algorithm that respects these entropy bounds resulting in less degenerate, more contextual, and "human-like" language generation in open-ended text generation settings.

Significant developments in techniques such as encoder-decoder models have enabled us to represent information comprising multiple modalities. This information can further enhance many downstream tasks in the field of information retrieval and natural language processing; however, improvements in multi-modal techniques and their performance evaluation require large-scale multi-modal data which offers sufficient diversity. Multi-lingual modeling for a variety of tasks like multi-modal summarization, text generation, and translation leverages information derived from high-quality multi-lingual annotated data. In this work, we present the current largest multi-lingual multi-modal summarization dataset (M3LS), and it consists of over a million instances of document-image pairs along with a professionally annotated multi-modal summary for each pair. It is derived from news articles published by British Broadcasting Corporation(BBC) over a decade and spans 20 languages, targeting diversity across five language roots, it is also the largest summarization dataset for 13 languages and consists of cross-lingual summarization data for 2 languages. We formally define the multi-lingual multi-modal summarization task utilizing our dataset and report baseline scores from various state-of-the-art summarization techniques in a multi-lingual setting. We also compare it with many similar datasets to analyze the uniqueness and difficulty of M3LS.