United States

Sequential recommender systems aim to model usersâ€™ evolving interests from their historical behaviors, and hence make customized time-relevant recommendations. Compared with traditional models, deep learning approaches such as CNN and RNN have achieved remarkable advancements in recommendation tasks. Recently, the BERT framework also emerges as a promising method, benefited from its self-attention mechanism in processing sequential data. However, one limitation of the original BERT framework is that it only considers one input source of the natural language tokens. It is still an open question to leverage various types of information under the BERT framework. Nonetheless, it is intuitively appealing to utilize other side information, such as item category or tag, for more comprehensive depictions and better recommendations. In our pilot experiments, we found naive approaches, which directly fuse types of side information into the item embeddings, usually bring very little or even negative effects. Therefore, in this paper, we propose the NOn-inVasive self-Attention mechanism (NOVA) to leverage side information effectively under the BERT framework. NOVA makes use of side information to generate better attention distribution, rather than directly altering the item embeddings, which may cause information overwhelming. We validate the NOVA-BERT model on both public and commercial datasets, and our method can stably outperform the state-of-the-art models with negligible computational overheads.

AAAI 2021

Noninvasive Self-Attention for Side Information Fusion in Sequential Recommendation

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 synthesis of materials using the principle of thermogravimetric analysis to discover new anticorrosive paints requires several costly experiments. This paper presents an approach combining empirical data and domain analytical models to reduce the number of real experiments required to obtain the desired synthesis. The main idea is to predict the behavior of the synthesis of two materials with well-defined mass proportions as a function of temperature. As no exact equational model exists to predict the new material, we integrate a machine learning approach circumscribed by existing domain analytical models such as heating and kinetics equations in order to derive a generative model of augmented experiments. Extensive empirical evaluation shows that using machine learning approach guided by analytic models, it is possible to substantially reduce the number of needed physical experiments without losing the approximation quality.

Augmented Experiment in Material Engineering Using Machine Learning

Recently, deep neural networks (DNNs) have achieved excellent performance on time series classification. However, DNNs require large amounts of labeled data for supervised training. Although data augmentation can alleviate this problem, the standard approach assigns the same label to all augmented samples from the same source. This leads to the expansion of the data distribution such that the classification boundaries may be even harder to determine. In this paper, we propose Joint-label learning by Dual Augmentation (JobDA), which can enrich the training samples without expanding the distribution of the original data. Instead, we apply simple transformations to the time series and give these modified time series new labels, so that the model has to distinguish between these and the original data, as well as separating the original classes. This approach sharpens the boundaries around the original time series, and results in superior classification performance. We use Time Series Warping for our transformations: We shrink and stretch different regions of the original time series, like a fun-house mirror. Experiments conducted on extensive time-series datasets show that JobDA can improve the model performance on small datasets. Moreover, we verify that JobDA has better generalization ability compared with conventional data augmentation, and the visualization analysis further demonstrates that JobDA can learn more compact clusters.

Joint-Label Learning by Dual Augmentation for Time Series Classification

In a graph, a k-plex is a vertex set in which every vertex is not adjacent to at most k vertices of this set. The maximum k-plex problem, which asks for the largest k-plex from the given graph, is a key primitive in a variety of real-world applications like community detection and so on. In the paper, we develop an exact algorithm, Maplex, for solving this problem in real world graphs practically. Based on the existing first-order and the novel second-order reduction rules, we design a powerful preprocessing method which efficiently removes redundant vertices and edges for Maplex. Also, the graph color heuristic is widely used for overestimating the maximum clique of a graph. For the first time, we generalize this technique for bounding the size of maximum k-plex in Maplex. Experiments are carried out to compare our algorithm with other state-of-the-art solvers on a wide range of publicly available graphs. Maplex outperforms all other algorithms on large real world graphs and is competitive with existing solvers on artificial dense graphs. Finally, we shed light on the effectiveness of each key component of Maplex.

Improving Maximum k-plex Solver via Second-Order Reduction and Graph Color Bounding

This paper proposes human-interpretable learning of aspect-based sentiment analysis (ABSA), employing the recently introduced Tsetlin Machines (TMs). We attain interpretability by converting the intricate position-dependent textual semantics into binary form, mapping all the features into bag-of-words (BOWs). The binary form BOWs are encoded so that the information on the aspect and context words are nearly lossless for sentiment classification. We further adapt the BOWs as input to the TM, enabling learning of aspect-based sentiment patterns in propositional logic. To evaluate interpretability and accuracy, we conducted experiments on two widely used ABSA datasets of SemEval 2014: Restaurant 14 and Laptop 14. The experiments show how each relevant feature takes part in conjunctive clauses that contain the context information for the corresponding aspect word, demonstrating human-level interpretability. At the same time, the obtained accuracy is competitive with existing neural network models, reaching 78.02% on Restaurant 14 and 73.51% on Laptop 14.

Human-Level Interpretable Learning for Aspect-Based Sentiment Analysis

We address the problem of efficient exploration for transition model learning in the relational model-based reinforcement learning setting without extrinsic goals or rewards. Inspired by human curiosity, we propose goal-literal babbling (GLIB), a simple and general method for exploration in such problems. GLIB samples relational conjunctive goals that can be understood as specific, targeted effects that the agent would like to achieve in the world, and plans to achieve these goals using the transition model being learned. We provide theoretical guarantees showing that exploration with GLIB will converge almost surely to the ground truth model. Experimentally, we find GLIB to strongly outperform existing methods in both prediction and planning on a range of tasks, encompassing standard PDDL and PPDDL planning benchmarks and a robotic manipulation task implemented in the PyBullet physics simulator. Video: https://youtu.be/F6lmrPT6TOY Code: https://git.io/JIsTB

GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling

Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. 	Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.

Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

Monte Carlo tree search (MCTS) has achieved state-of-the-art results in many domains such as Go and Atari games when combining with deep neural networks (DNNs). When more simulations are executed, MCTS can achieve higher performance but also requires enormous amounts of CPU and GPU resources. However, not all states require a long searching time to identify the best action that the agent can find. For example, in 19x19 Go and NoGo, we found that for more than half of the states, the best action predicted by DNN remains unchanged even after searching 2 minutes. This implies that a significant amount of resources can be saved if we are able to stop the searching earlier when we are confident with the current searching result. In this paper, we propose to achieve this goal by predicting the uncertainty of the current searching status and use the result to decide whether we should stop searching. With our algorithm, called Dynamic Simulation MCTS (DS-MCTS), we can speed up a NoGo agent trained by AlphaZero 2.5 times faster while maintaining a similar winning rate, which is critical for training and conducting experiments. Also, under the same average simulation count, our method can achieve a 61\% winning rate against the original program.

Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search

We investigate response selection for multi-turn conversation in retrieval-based chatbots. Existing studies pay more attention to the matching between utterances and responses by calculating the matching score based on learned features, leading to insufficient model reasoning ability. In this paper, we propose a graph- reasoning network (GRN) to address the problem. GRN first conducts pre-training based on ALBERT using next utterance prediction and utterance order prediction tasks specifically devised for response selection. These two customized pre-training tasks can endow our model with the ability of capturing semantical and chronological dependency between utterances. We then fine-tune the model on an integrated network with sequence reasoning and graph reasoning structures. The sequence reasoning module conducts inference based on the highly summarized context vector of utterance-response pairs from the global perspective. The graph reasoning module conducts the reasoning on the utterance-level graph neural network from the local perspective. Experiments on two conversational reasoning datasets show that our model can dramatically outperform the strong baseline methods and can achieve performance which is close to human-level.

A Graph Reasoning Network for Multi-Turn Response Selection via Customized Pre-Training

Many problems in machine learning and game theory can be formulated as saddle-point problems, for which various first-order methods have been developed and proven efficient in practice. Under the general convex-concave assumption, most first-order methods only guarantee an ergodic convergence rate, that is, the uniform averages of the iterates converge at a O(1/T) rate in terms of the saddle-point residual. However, numerically, the iterates themselves can often converge much faster than the uniform averages. This observation motivates increasing averaging schemes that put more weight on later iterates, in contrast to the usual uniform averaging. We show that such increasing averaging schemes, applied to various first-order methods, are able to preserve the O(1/T) convergence rate with no additional assumptions or computational overhead. Extensive numerical experiments on zero-sum game solving, market equilibrium computation and image denoising demonstrate the effectiveness of the proposed schemes. In particular, the increasing averages consistently outperform the uniform averages in all test problems by orders of magnitude. When solving matrix and extensive-form games, increasing averages consistently outperform the last iterates as well. For matrix games, a first-order method equipped with increasing averaging outperforms the highly competitive CFR+ algorithm.

Increasing Iterate Averaging for Solving Saddle-Point Problems

The development of a satisfying and rigorous mathematical understanding of the performance of neural networks is a major challenge in artificial intelligence. Against this background, we study the expressive power of neural networks through the example of the classical NP-hard Knapsack Problem. Our main contribution is a class of recurrent neural networks (RNNs) with rectified linear units that are iteratively applied to each item of a Knapsack instance and thereby compute optimal or provably good solution values. We show that an RNN of depth four and width depending quadratically on the profit of an optimum Knapsack solution is sufficient to find optimum Knapsack solutions. We also prove the following tradeoff between the size of an RNN and the quality of the computed Knapsack solution: for Knapsack instances consisting of n items, an RNN of depth five and width w computes a solution of value at least 1 - O(n^2 sqrt(w)) times the optimum solution value. Our results build upon a classical dynamic programming formulation of the Knapsack Problem as well as a careful rounding of profit values that are also at the core of the well-known fully polynomial-time approximation scheme for the Knapsack Problem. Finally, we point out that our results can be generalized to many other combinatorial optimization problems that admit dynamic programming solution methods, such as various Shortest Path Problems, the Longest Common Subsequence Problem, and the Traveling Salesperson Problem.

Downloads

Next from AAAI 2021

Augmented Experiment in Material Engineering Using Machine Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Augmented Experiment in Material Engineering Using Machine Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads