A surrogate function is often employed to reduce the number of objective function evaluations for optimization. However, the effect of using a surrogate model in evolutionary approaches has not been theoretically investigated. This paper theoretically analyzes the information-geometric optimization framework using a surrogate function. The value of the expected objective function under the candidate sampling distribution is used as the measure of progress of the algorithm. We assume that the surrogate function is maintained so that the population version of the Kendall's rank correlation coefficient between the surrogate function and the objective function under the candidate sampling distribution is greater than or equal to a predefined threshold. We prove that information-geometric optimization using such a surrogate function leads to a monotonic decrease in the expected objective function value if the threshold is sufficiently close to one. The acceptable threshold value is analyzed for the case of the information-geometric optimization instantiated with Gaussian distributions, i.e., the rank-$\mu$ update CMA-ES, on a convex quadratic objective function. As an alternative to the Kendall's rank correlation coefficient, we investigate the use of the Pearson correlation coefficient between the weights assigned to candidate solutions based on the objective function and the surrogate function.
Deep hashing has been widely applied to large-scale image retrieval tasks owing to efficient computation and low storage cost by encoding high-dimensional image data into binary codes. Since binary codes do not contain as much information as float features, the essence of binary encoding is preserving the main context to guarantee retrieval quality. However, the existing hashing methods have great limitations on suppressing redundant background information and accurately encoding from Euclidean space to Hamming space by a simple sign function. In order to solve these problems, a Cross-Scale Context Extracted Hashing Network (CSCE-Net) is proposed in this paper. Firstly, we design a two-branch framework to capture fine-grained local information while maintaining high-level global semantic information. Besides, Attention guided Information Extraction module (AIE) is introduced between two branches, which suppresses areas of low context information cooperated with global sliding windows. Unlike previous methods, our CSCE-Net learns a content-related Dynamic Sign Function (DSF) to replace the original simple sign function. Therefore, the proposed CSCE-Net is context-sensitive and able to perform well on accurate image binary encoding. We further demonstrate that our CSCE-Net is superior to the existing hashing methods, which improves retrieval performance on standard benchmarks.
With the development of Web 3.0 which emphasizes decentralization, blockchain technology ushers in its revolution and also brings numerous challenges, particularly in the field of cryptocurrency. Recently, a large number of criminal behaviors continuously emerge on blockchain, such as Ponzi schemes and phishing scams, which severely endanger decentralized finance. Existing graph-based abnormal behavior detection methods on blockchain usually focus on constructing homogeneous transaction graphs without distinguishing the heterogeneity of nodes and edges, resulting in partial loss of transaction pattern information. Although existing heterogeneous modeling methods can depict richer information through metapaths, the extracted metapaths generally neglect temporal dependencies between entities and do not reflect real behavior. In this paper, we introduce Time-aware Metapath Feature Augmentation (TMFAug) as a plug-and-play module to capture the real metapath-based transaction patterns during Ponzi scheme detection on Ethereum. The proposed module can be adaptively combined with existing graph-based Ponzi detection methods. Extensive experimental results show that our TMFAug can help existing Ponzi detection methods achieve significant performance improvements on the Ethereum dataset, indicating the effectiveness of heterogeneous temporal information for Ponzi scheme detection.
Target-specific stance detection on social media, which aims at classifying a textual data instance such as a post or a comment into a stance class of a target issue, has become an emerging opinion mining paradigm of importance. An example application would be to overcome vaccine hesitancy in combating the coronavirus pandemic. However, existing stance detection strategies rely merely on the individual instances which cannot always capture the expressed stance of a given target. In response, we address a new task called conversational stance detection which is to infer the stance towards a given target (e.g., COVID-19 vaccination) when given a data instance and its corresponding conversation thread. To tackle the task, we first propose a benchmarking conversational stance detection (CSD) dataset with annotations of stances and the structures of conversation threads among the instances based on six major social media platforms in Hong Kong. To infer the desired stances from both data instances and conversation threads, we propose a model called Branch-BERT that incorporates contextual information in conversation threads. Extensive experiments on our CSD dataset show that our proposed model outperforms all the baseline models that do not make use of contextual information. Specifically, it improves the F1 score by 10.3% compared with the state-of-the-art method in the SemEval-2016 Task 6 competition. This shows the potential of incorporating rich contextual information on detecting target-specific stances on social media platforms and implies a more practical way to construct future stance detection tasks.
Audio captioning is the task of generating captions that describe the content of audio clips. In the real world, many objects produce similar sounds. It is difficult to identify these auditory ambiguous sound events with access to audio information only. How to accurately recognize ambiguous sounds is a major challenge for audio captioning systems. In this work, inspired by the audio-visual multi-modal perception of human beings, we propose visually-aware audio captioning, which makes use of visual information to help the recognition of ambiguous sounding objects. Specifically, we introduce an off-the-shelf visual encoder to process the video inputs, and incorporate the extracted visual features into an audio captioning system. Furthermore, to better exploit complementary contexts from redundant audio-visual streams, we propose an audio-visual attention mechanism that integrates audio and visual information adaptively according to their confidence levels. Experimental results on AudioCaps, the largest publicly available audio captioning dataset, show that the proposed method achieves significant improvement over a strong baseline audio captioning system and is on par with the state-of-the-art result.
Targeted studies testing knowledge of subject-verb agreement (SVA) indicate that pre-trained language models encode syntactic information. We assert that if models robustly encode subject-verb agreement, they should be able to identify when agreement is correct and when it is incorrect. To that end, we propose grammatical error detection as a diagnostic probe to evaluate token-level contextual representations for their knowledge of SVA. We evaluate contextual representations at each layer from five pre-trained English language models: BERT, XLNet, GPT-2, RoBERTa, and ELECTRA. We leverage public annotated training data from both English second language learners and Wikipedia edits, and report results on manually crafted stimuli for subject-verb agreement. We find that masked language models linearly encode information relevant to the detection of SVA errors, while the autoregressive models perform on par with our baseline. However, we also observe a divergence in performance when probes are trained on different training sets, and when they are evaluated on different syntactic constructions, suggesting the information pertaining to SVA error detection is not robustly encoded.
Adversarial examples, generated by carefully crafted perturbation, have attracted considerable attention in research fields. Recent works have argued that the existence of the robust and non-robust features is a primary cause of the adversarial examples, and investigated their internal interactions in the feature space. In this paper, we propose a way of explicitly distilling feature representation into the robust and non-robust features, using Information Bottleneck. Specifically, we inject noise variation to each feature unit and evaluate the information flow in the feature representation to dichotomize feature units either robust or non-robust, based on the noise variation magnitude. Through comprehensive experiments, we demonstrate that the distilled features are highly correlated with adversarial prediction, and they have human-perceptible semantic information by themselves. Furthermore, we present an attack mechanism intensifying the gradient of non-robust features that is directly related to the model prediction, and validate its effectiveness of breaking model robustness.
Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information. Recent studies show that current models rely on shallow heuristics to predict solutions and could be easily misled by small textual perturbations. To address this problem, we propose a Textual Enhanced Contrastive Learning framework, which enforces the models to distinguish semantically similar examples while holding different mathematical logic. We adopt a self-supervised manner strategy to enrich examples with subtle textual variance by textual reordering or problem re-construction. We then retrieve the hardest to differentiate samples from both equation and textual perspectives and guide the model to learn their representations. Experimental results show that our method achieves state-of-the-art on both widely used benchmark datasets and also exquisitely designed challenge datasets in English and Chinese. \footnote{Our code and data is available at \url{https://github.com/yiyunya/Textual_CL_MWP}
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog systems, especially for the many real world tasks that have a large and growing number of intents and slot types. While zero shot learning approaches that require no labeled examples -- only features and auxiliary information -- have been proposed only for slot labeling, we show that one can profitably perform joint zero-shot intent classification and slot labeling. We demonstrate the value of capturing dependencies between intents and slots, and between different slots in an utterance in the zero shot setting. We describe NN architectures that translate between word and sentence embedding spaces, and demonstrate that these modifications are required to enable zero shot learning for this task. We show a substantial improvement over strong baselines and explain the intuition behind each architectural modification through visualizations and ablation studies.
While modern Text-to-Speech (TTS) systems can produce speech rated highly in terms of subjective evaluation, the distance between real and synthetic speech distributions remains understudied, where we use the term \textit{distribution} to mean the sample space of all possible real speech recordings from a given set of speakers; or of the synthetic samples that could be generated for the same set of speakers. We evaluate the distance of real and synthetic speech distributions along the dimensions of the acoustic environment, speaker characteristics and prosody using a range of speech processing measures and the respective Wasserstein distances of their distributions. We reduce these distribution distances along said dimensions by providing utterance-level information derived from the measures to the model and show they can be generated at inference time. The improvements to the dimensions translate to overall distribution distance reduction approximated using Automatic Speech Recognition (ASR) by evaluating the fitness of the synthetic data as training data.