United States

With the capability of trading accuracy for latency on-the-fly, the technique of adaptive early-exit inference has emerged as a promising line of research to accelerate the deep learning inference. However, studies in this line of research commonly use a group of thresholds to control the accuracy-latency trade-off, where a thorough and general methodology on how to determine these thresholds has not been conducted yet, especially with regard to the common requirements of average inference latency. To address this issue and enable latency-aware adaptive early-exit inference, in the present paper, we approximately formulate the threshold determination problem of finding the accuracy-maximum threshold setting that meets a given average latency requirement, and then propose a threshold determination method to tackle our formulated non-convex problem. Theoretically, we prove that, for certain parameter settings, our method finds an approximate stationary point of the formulated problem. Empirically, on top of various models across multiple datasets (CIFAR-10, CIFAR-100, ImageNet and two time-series datasets), we show that our method can well handle the average latency requirements, and consistently finds good threshold settings in negligible time.

AAAI 2021

Empowering Adaptive Early-Exit Inference with Latency Awareness

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

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. 

With the rapid evolution of social media, fake news has become a significant social problem, which cannot be addressed in a timely manner using manual investigation. This has motivated numerous studies on automating fake news detection. Most studies explore supervised training models with different modalities (e.g., text, images, and propagation networks) of news records to identify fake news. However, the performance of such techniques generally drops if news records are coming from different domains (e.g., politics, entertainment), especially for domains that are unseen or rarely-seen during training. As motivation, we empirically show that news records from different domains have significantly different word usage and propagation patterns. Furthermore, due to the sheer volume of unlabelled news records, it is challenging to select news records for manual labelling so that the domain-coverage of the labelled dataset is maximised. Hence, this work: (1) proposes a novel framework that jointly preserves domain-specific and cross-domain knowledge in news records to detect fake news from different domains; and (2) introduces an unsupervised technique to select a set of unlabelled informative news records for manual labelling, which can be ultimately used to train a fake news detection model that performs well for many domains while minimizing the labelling cost. Our experiments show that the integration of the proposed fake news model and the selective annotation approach achieves state-of-the-art performance for cross-domain news datasets, while yielding notable improvements for rarely-appearing domains in news datasets.

Embracing Domain Differences in Fake News: Cross-Domain Fake News Detection Using Multi-Modal Data

This paper studies defense mechanisms against model inversion (MI) attacks -- a type of privacy attacks aimed at inferring information about the training data distribution given the access to a target machine learning model. Existing defense mechanisms rely on model-specific heuristics or noise injection. While being able to mitigate attacks, existing methods significantly hinder model performance. There remains a question of how to design a defense mechanism that is applicable to a variety of models and achieves better utility-privacy tradeoff.

In this paper, we propose the Mutual Information Regularization based Defense (MID) against MI attacks. The key idea is to limit the information about the model input contained in the prediction, thereby limiting the ability of an adversary to infer the private training attributes from the model prediction. Our defense principle is model-agnostic and we present tractable approximations to the regularizer for linear regression, decision trees, and neural networks, which have been successfully attacked by prior work if not attached with any defenses. We present a formal study of MI attacks by devising a rigorous game-based definition and quantifying the associated information leakage. Our theoretical analysis sheds light on the inefficacy of DP in defending against MI attacks, which has been empirically observed in several prior works. Our experiments demonstrate that MID leads to state-of-the-art performance for a variety of MI attacks, target models and datasets.

Improving Robustness to Model Inversion Attacks via Mutual Information Regularization

We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast. Solving this problem enables the application of conversational agents in many real-world scenarios, e.g., recommendation and psychotherapy. The dominant paradigm for tackling this problem is to 1) train a next-turn keyword classifier, and 2) train a keyword-augmented response retrieval model. However, existing approaches in this paradigm have two limitations: 1) the training and evaluation datasets for next-turn keyword classification are directly extracted from conversations without human annotations, thus, they are noisy and have low correlation with human judgements, and 2) during keyword transition, the agents solely rely on the similarities between word embeddings to move closer to the target keyword, which may not reflect how humans converse. In this paper, we assume that human conversations are grounded on commonsense and propose a keyword-guided neural conversational model that can leverage external commonsense knowledge graphs (CKG) for both keyword transition and response retrieval. Automatic evaluations suggest that commonsense improves the performance of both next-turn keyword prediction and keyword-augmented response retrieval. In addition, both self-play and human evaluations show that our model produces responses with smoother keyword transition and reaches the target keyword faster than competitive baselines.

Keyword-Guided Neural Conversational Model

Rationality and emotion are two fundamental elements of humans. Endowing agents with rationality and emotion has been one of the major milestones in AI. However, in the field of conversational AI, most existing models only specialize in one aspect and neglect the other, which often leads to dull or unrelated responses. In this paper, we hypothesize that combining rationality and emotion into conversational agents can improve response quality. To test the hypothesis, we focus on one fundamental aspect of rationality, i.e., commonsense, and propose CARE, a novel model for commonsense-aware emotional response generation. Specifically, we first propose a framework to learn and construct commonsense-aware emotional latent concepts of the response given an input message and a desired emotion. We then propose three methods to collaboratively incorporate the latent concepts into response generation. Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.

CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

We solve a challenging yet practically useful variant of 3D Bin Packing Problem (3D-BPP). In our problem, the agent has limited information about the items to be packed into a single bin, and an item must be packed immediately after its arrival without buffering or readjusting. The item's placement also subjects to the constraints of order dependence and physical stability. We formulate this online 3D-BPP as a constrained Markov decision process (CMDP). To solve the problem, we propose an effective and easy-to-implement constrained deep reinforcement learning (DRL) method under the actor-critic framework. In particular, we introduce a prediction-and-projection scheme: The agent first predicts a feasibility mask for the placement actions as an auxiliary task and then uses the mask to modulate the action probabilities output by the actor during training. Such supervision and projection facilitate the agent to learn feasible policies very efficiently. Our method can be easily extended to handle lookahead items, multi-bin packing, and item re-orienting. We have conducted extensive evaluation showing that the learned policy significantly outperforms the state-of-the-art methods. A preliminary user study even suggests that our method might attain a human-level performance.

Online 3D Bin Packing with Constrained Deep Reinforcement Learning

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens of various types. For example, to describe a musical note, one needs separate tokens to indicate the noteâ€™s pitch, duration, velocity (dynamics), and placement (onset time) along the time grid. While different types of tokens may possess different properties, existing models usually treat them equally, in the same way as modeling words in natural languages. In this paper, we present a conceptually different approach that explicitly takes into account the type of the tokens, such as note types and metric types. And, we propose a new Transformer decoder architecture that uses different feed-forward heads to model tokens of different types. With an expansion-compression trick, we convert a piece of music to a sequence of compound words by grouping neighboring tokens, greatly reducing the length of the token sequences. We show that the resulting model can be viewed as a learner over dynamic directed hypergraphs. And, we employ it to learn to compose expressive Pop piano music of full-song length (involving up to 10K individual tokens per song), both conditionally and unconditionally. Our experiment shows that, compared to state-of-the-art models, the proposed model converges 5 to 10 times faster at training (i.e., within a day on a single GPU with 11 GB memory), and with comparable quality in the generated music

Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs

Keyphrase Generation compresses a document into some highly-summative phrases, which is an important task in natural language processing. Most state-of-the-art adopt greedy search or beam search decoding methods. These two decoding methods generate a large number of duplicated keyphrases and are time-consuming. Moreover, beam search only predicts a fixed number of keyphrases for different documents. In this paper, we propose an adaptive generation model-AdaGM, which is mainly inspired by the importance of the first words in keyphrase generation. In AdaGM, a novel reset state training mechanism is proposed to maximize the difference in the predicted first words. To ensure the discreteness and get an appropriate number of keyphrases according to the content of the document adaptively, we equip beam search with a highly effective filter mechanism. Experiments on five public datasets demonstrate the proposed model can generate marginally less duplicated and more accurate keyphrases. The codes of AdaGM are available at: https://github.com/huangxiaolist/adaGM.

Adaptive Beam Search Decoding for Discrete Keyphrase Generation

Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a  residual structure and theoretical guarantees. Moreover, most LISTA methods use the soft thresholding function, which has been found to cause a large estimation bias. Therefore, we propose a  thresholding function for ELISTA instead of soft thresholding. From a theoretical perspective, we prove that our method attains linear convergence. Through ablation experiments, the improvements of our method on the network structure and the thresholding function are verified in practice. Extensive empirical results verify the advantages of our method.

Learned Extragradient ISTA with Interpretable Residual Structures for Sparse Coding

While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real world settings.
In many such cases although test data might not be available, broad specifications about the types of perturbations (such as an unknown degree of rotation) may be known.
We consider a setup where robustness is expected over an unseen test domain that is not i.i.d. but deviates from the training domain.
While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes.
We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space, without having access to the data from the test domain.
Our adversarial training solves a min-max optimization problem, with the inner maximization generating adversarial perturbations,
and the outer minimization finding model parameters by optimizing the loss on adversarial perturbations generated from the inner maximization.
We demonstrate the applicability of our approach on three types of naturally occurring perturbations --- object-related shifts, geometric transformations, and common image corruptions.
Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
We demonstrate the usefulness of the proposed approach by showing the robustness gains of deep neural networks trained using our adversarial training on MNIST, CIFAR-10, and a new variant of the CLEVR dataset.

Attribute-Guided Adversarial Training for Robustness to Natural Perturbations

Entities, as the essential elements in relation extraction tasks, exhibit certain structure. In this work, we formulate such entity structure as distinctive dependencies between mention pairs. We then propose SSAN, which incorporates these structural dependencies within the standard self-attention mechanism and throughout the overall encoding stage. Specifically, we design two alternative transformation modules inside each self-attention building block to produce attentive biases so as to adaptively regularize its attention flow. Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN. It significantly outperforms competitive baselines, achieving new state-of-the-art results on three popular document-level relation extraction datasets. We further provide ablation and visualization to show how the entity structure guides the model for better relation extraction. Our code is publicly available.

Downloads

Next from AAAI 2021

Embracing Domain Differences in Fake News: Cross-Domain Fake News Detection Using Multi-Modal Data

Similar lecture

Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings

.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

Embracing Domain Differences in Fake News: Cross-Domain Fake News Detection Using Multi-Modal Data

Similar lecture

Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings

Downloads