United States

Regularization of (deep) learning models can be realized at the model, loss, or data level. As a technique somewhere in-between loss and data, label smoothing turns deterministic class labels into probability distributions, for example by uniformly distributing a certain part of the probability mass over all classes. A predictive model is then trained on these distributions as targets, using cross-entropy as loss function. While this method has shown improved performance compared to non-smoothed cross-entropy, we argue that the use of a smoothed though still precise probability distribution as a target can be questioned from a theoretical perspective. As an alternative, we propose a generalized technique called label relaxation, in which the target is a set of probabilities represented in terms of an upper probability distribution. This leads to a genuine relaxation of the target instead of a distortion, thereby reducing the risk of incorporating an undesirable bias in the learning process. Methodically, label relaxation leads to the minimization of a novel type of loss function, for which we propose a suitable closed-form expression for model optimization. The effectiveness of the approach is demonstrated in an empirical study on image data.

AAAI 2021

From Label Smoothing to Label Relaxation

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

The Mixup method, which uses linearly interpolated data, has emerged as an effective data augmentation tool to improve generalization performance and the robustness to adversarial examples. The motivation is to curtail undesirable oscillations by its implicit model constraint to behave linearly at in-between observed data points and promote smoothness. In this work, we formally investigate this premise, propose a way to impose smoothness constraints explicitly, and extend it to incorporate implicit model constraints. First, we derive a new function class composed of kernel-convoluted models (KCM) where the smoothness constraint is directly imposed by locally averaging the original functions with a kernel function. Second, we propose to incorporate the Mixup method into KCM to expand the domains of smoothness. In both cases of the KCM and the KCM adapted with the Mixup, we provide risk analysis, respectively, under mild conditions on kernel functions. As a result, we show that the upper bound of the excess risk over a new function class is not slower than that of the excess risk over the original function class. Using CIFAR-10 and CIFAR-100 datasets, our experiments demonstrate that the KCM with the Mixup outperforms the Mixup method in terms of generalization and robustness to adversarial examples.

Kernel-Convoluted Deep Neural Networks with Data Augmentation

Regret bounds of online kernel selection in a finite kernel set have been well studied, having at least an order O( âˆš NT) of magnitude after T rounds, where N is the number of candidate kernels. But it is still an unsolved problem to achieve sublinear regret bounds of online kernel selection in a continuous kernel space under different learning frameworks. In this paper, to represent different learning frameworks of online kernel selection, we divide online kernel selection approaches in a continuous kernel space into two categories according to the order of selection and training at each round. Then we construct a surrogate hypothesis space that contains all the candidate kernels with bounded norms and inner products, representing the continuously varying hypothesis space. Finally, we decompose the regrets of the proposed online kernel selection categories into different types of instantaneous regrets in the surrogate hypothesis space, and derive optimal regret bounds of order O( âˆš T) of magnitude under mild assumptions, independent of the cardinality of the continuous kernel space. Empirical studies verified the correctness of the theoretical regret analyses.

Regret Bounds for Online Kernel Selection in Continuous Kernel Space

Node classification is an important problem on graphs. While recent advances in graph neural networks achieve promising performance, they require abundant labeled nodes for training. However, in many practical scenarios, there often exist novel classes in which only one or a few labeled nodes are available as supervision, known as few-shot node classification. Although meta-learning has been widely used in vision and language domains to address few-shot learning, its adoption on graphs has been limited. In particular, graph nodes in a few-shot task are not independent and relate to each other. To deal with this, we propose a novel model called Relative and Absolute Location Embedding (RALE) hinged on the concept of hub nodes. Specifically, RALE captures the task-level dependency by assigning each node a relative location within a task, as well as the graph-level dependency by assigning each node an absolute location on the graph to further align different tasks toward learning a transferable prior. Finally, extensive experiments on three public datasets demonstrate the state-of-the-art performance of RALE.

Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph

Participatory budgeting (PB) is a democratic paradigm whereby voters decide on a set of projects to fund with  a limited budget. We consider PB in a setting where voters report ordinal preferences over projects and have (possibly) asymmetric weights. We propose proportional representation axioms and clarify how they fit into other preference aggregation settings, such as multi-winner voting and approval-based multi-winner voting. As a result of our study, we also discover a new solution concept for approval-based multi-winner voting, which we call Inclusion PSC (IPSC). IPSC is stronger than proportional justified representation (PJR), incomparable to extended justified representation (EJR), and yet compatible with EJR. The well-studied Proportional Approval Voting (PAV)  rule produces a committee that satisfies both EJR and IPSC; however, both these axioms can also be satisfied by an algorithm that runs in polynomial-time.

Proportionally Representative Participatory Budgeting with Ordinal Preferences

Social relation extraction (SRE for short), which aims to infer the social relation between two people in daily life, has been demonstrated to be of great value in reality. Existing methods for SRE consider extracting social relation only from unimodal information such as text or image, ignoring the high coupling of multimodal information. Moreover, previous studies overlook the serious unbalance distribution on social relations. To address these issues, this paper proposes FL-MSRE, a few-shot learning based approach to extracting social relations from both texts and face images. Considering the lack of multimodal social relation datasets, this paper also presents three multimodal datasets annotated from four classical masterpieces and corresponding TV series. Inspired by the success of BERT, we propose a strong BERT based baseline to extract social relation from text only. FL-MSRE is empirically shown to outperform the baseline significantly. This demonstrates that using face images benefits text-based SRE. Further experiments also show that using two faces from different images achieves similar performance as from the same image. This means that FL-MSRE is suitable for a wide range of SRE applications where the faces of two people can only be collected from different images.

FL-MSRE: A Few-Shot Learning Based Approach to Multimodal Social Relation Extraction

Currently, text classification studies mainly focus on training classifiers by using textual input only, or enhancing semantic features by introducing external knowledge (e.g., hand-craft lexicons and domain knowledge). In contrast, some intrinsic statistical features of the corpus, like word frequency and distribution over labels, are not well exploited. Compared with external knowledge, the statistical features are deterministic and naturally compatible with corresponding tasks. In this paper, we propose an Adaptive Gate Network (AGN) to consolidate semantic representation with statistical features selectively. In particular, AGN encodes statistical features through a variational component and merges information via a well-designed valve mechanism. The valve adapts the information flow into the classifier according to the confidence of semantic features in decision making, which can facilitate training a robust classifier and can address the overfitting caused by using statistical features. Extensive experiments on datasets of various scales show that, by incorporating statistical information, AGN can improve the classification performance of CNN, RNN, Transformer, and Bert based models effectively. The experiments also indicate the robustness of AGN against adversarial attacks of manipulating statistical information.

Merging Statistical Feature via Adaptive Gate for Improved Text Classification

While frame-independent predictions with deep neural networks have become the prominent solutions to many computer vision tasks, the potential benefits of utilizing correlations between frames have received less attention. Even though probabilistic machine learning provides the ability to encode correlation as prior knowledge for inference, there is a tangible gap between the theory and practice of applying probabilistic methods to modern vision problems. For this, we derive a principled framework to combine information coupling between camera poses (translation and orientation) with deep models. We proposed a novel view kernel that generalizes the standard periodic kernel in SO(3). We show how this soft-prior knowledge can aid several pose-related vision tasks like novel view synthesis and predict arbitrary points in the latent space of generative models, pointing towards a range of new applications for inter-frame reasoning.

Gaussian Process Priors for View-Aware Inference

Behavior Trees (BTs) have attracted much attention in the robotics field in recent years, which generalize existing control architectures and bring unique advantages for building robot systems. Automated synthesis of BTs can reduce human workload and build behavior models for complex tasks beyond the ability of human design, but theoretical studies are almost missing in existing methods because it is difficult to conduct formal analysis with the classic BT representations. As a result, they may fail in tasks that are actually solvable. This paper proposes BT expansion, an automated planning approach to building intelligent robot behaviors with BTs, and proves the soundness and completeness through the state-space formulation of BTs. The advantages of blended reactive planning and acting are formally discussed through the region of attraction of BTs, by which robots with BT expansion are robust to any resolvable external disturbances. Experiments with a mobile manipulator and test sets are simulated to validate the effectiveness and efficiency, where the proposed algorithm surpasses the baseline by virtue of its soundness and completeness. To the best of our knowledge, it is the first time to leverage the state-space formulation to synthesize BTs with a complete theoretical basis.

BT Expansion: A Sound and Complete Algorithm for Behavior Planning of Intelligent Robots with Behavior Trees

In the influence maximization (IM) problem, we are given a social network and a budget k, and we look for a set of k nodes in the network, called seeds, that maximize the expected number of nodes that are reached by an influence cascade generated by the seeds, according to some stochastic model for influence diffusion. Extensive studies have been done on the IM problem, since his definition by Kempe, Kleinberg, and Tardos (2003). However, most of the work focuses on the non-adaptive version of the problem where all the k seed nodes must be selected before that the cascade starts. In this paper we study the adaptive IM, where the nodes are selected sequentially one by one, and the decision on the i-th seed can be based on the observed cascade produced by the first i-1 seeds. We focus on the full-adoption feedback in which we can observe the entire cascade of each previously selected seed and on the independent cascade model where each edge is associated with an independent probability of diffusing influence.

Previous works showed that there are constant upper bounds on the adaptivity gap, which compares the performance of an adaptive algorithm against a non-adaptive one, but the analyses used to prove these bounds only works for specific graph classes such as in-arborescences, out-arborescences, and one-directional bipartite graphs. Our main result is the first sub-linear upper bound that holds for any graph. Specifically, we show that the adaptivity gap is upper-bounded by âˆ›n+1, where n is the number of nodes in the graph. Moreover we improve over the known upper bound for in-arborescences from 2e/(e-1)â‰ˆ3.16 to 2eÂ²/(eÂ²-1)â‰ˆ2.31. Finally, we study Î±-bounded graphs, a class of undirected graphs in which the sum of node degrees higher than two is at most Î±, and show that the adaptivity gap is upper-bounded by âˆšÎ±+O(1). Moreover, we show that in 0-bounded graphs, i.e. undirected graphs in which each connected component is a path or a cycle, the adaptivity gap is at most 3eÂ³/(eÂ³-1)â‰ˆ3.16.

To prove our bounds, we introduce new techniques to relate adaptive policies with non-adaptive ones that might be of their own interest.

Better Bounds on the Adaptivity Gap of Influence Maximization under Full-Adoption Feedback

Recently, binary neural network (BNN) based super-resolution (SR) methods have enjoyed initial success in the SR field.  However, there is a noticeable  performance gap between the binarized model and the full-precision one. Furthermore, the batch normalization (BN) in binary SR networks introduces floating-point calculations, which is unfriendly to low-precision hardwares. Therefore, there is still room for improvement in terms of model performance and efficiency. Focusing on this issue, in this paper,  we first explore a novel binary training mechanism based on the feature distribution, allowing us to replace all BN layers with a simple training method.  Then, we construct a strong baseline by combining the highlights of recent binarization methods, which  already  surpasses the state-of-the-arts. Next, to train highly accurate binarized SR model, we also develop a lightweight network architecture and a multi-stage knowledge distillation strategy to  enhance the model representation ability.   Extensive experiments demonstrate that the proposed method not only presents advantages of lower computation as compared to conventional floating-point networks  but outperforms the state-of-the-art binary methods on the standard SR networks.

Downloads

Next from AAAI 2021

Kernel-Convoluted Deep Neural Networks with Data Augmentation

Similar lecture

Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Kernel-Convoluted Deep Neural Networks with Data Augmentation

Similar lecture

Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation

Downloads