United States

In recent years, there are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems (RS). In this paper, we summarize three key practical challenges of large-scale RL-based recommender systems: massive state and action spaces, high-variance environment, and the unspecific reward setting in recommendation. All these problems remain largely unexplored in the existing literature and make the application of RL challenging. We develop a model-based reinforcement learning framework, called GoalRec. Inspired by the ideas of world model (model-based), value function estimation (model-free), and goal-based RL, a novel disentangled universal value function designed for item recommendation is proposed. It can generalize to various goals that the recommender may have, and disentangle the stochastic environmental dynamics and high-variance reward signals accordingly. As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal. Based on the predicted environmental dynamics, the disentangled universal value function is related to the user&#39;s future trajectory instead of a monolithic state and a scalar reward. We demonstrate the superiority of GoalRec over previous approaches in terms of the above three practical challenges in a series of simulations and a real application.

AAAI 2021

Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation

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. 

In recent years, there are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems (RS). In this paper, we summarize three key practical challenges of large-scale RL-based recommender systems: massive state and action spaces, high-variance environment, and the unspecific reward setting in recommendation. All these problems remain largely unexplored in the existing literature and make the application of RL challenging. We develop a model-based reinforcement learning framework, called GoalRec. Inspired by the ideas of world model (model-based), value function estimation (model-free), and goal-based RL, a novel disentangled universal value function designed for item recommendation is proposed. It can generalize to various goals that the recommender may have, and disentangle the stochastic environmental dynamics and high-variance reward signals accordingly. As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal. Based on the predicted environmental dynamics, the disentangled universal value function is related to the user's future trajectory instead of a monolithic state and a scalar reward. We demonstrate the superiority of GoalRec over previous approaches in terms of the above three practical challenges in a series of simulations and a real application.

technical paper

The dramatic improvements in combinatorial optimization algorithms
over the last decades have had a major impact in artificial
intelligence, operations research, and beyond, but the output of
current state-of-the-art solvers is often hard to verify and is
sometimes wrong. For Boolean satisfiability (SAT) solvers proof
logging has been introduced as a way to certify correctness, but the
methods used seem hard to generalize to stronger paradigms. What is
more, even for enhanced SAT techniques such as parity (XOR) reasoning,
cardinality detection, and symmetry handling, it has remained beyond
reach to design practically efficient proofs in the standard DRAT
format. In this work, we show how to instead use pseudo-Boolean
inequalities with extension variables to concisely justify XOR
reasoning. Our experimental evaluation of a SAT solver integration
shows a dramatic decrease in proof logging and verification time
compared to existing DRAT methods. Since our method is a strict
generalization of DRAT, and readily lends itself to expressing also
0-1 programming and even constraint programming problems, we hope this
work points the way towards a unified approach for efficient
machine-verifiable proofs for a rich class of combinatorial
optimization paradigms.

Certifying Parity Reasoning Efficiently Using Pseudo-Boolean Proofs

Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or dependence of other tokens on each specific token. While beneficial, the quadratic complexity of self-attention on the input sequence length has limited its application to longer sequences - a topic being actively studied in the community. To address this limitation, we propose NystrÃ¶mformer - a model that exhibits favorable scalability as a function of sequence length. Our idea is based on adapting the NystrÃ¶m method to approximate standard self-attention with O(n) complexity. The scalability of NystrÃ¶mformer enables application to longer sequences with thousands of tokens. We perform evaluations on multiple downstream tasks on the GLUE benchmark and IMDB reviews with standard sequence length, and find that our NystrÃ¶mformer performs comparably, or in a few cases, even slightly better, than standard self-attention. On longer sequence tasks in the Long Range Arena (LRA) benchmark, NystrÃ¶mformer performs favorably relative to other efficient self-attention methods. Our code is available at https://github.com/mlpen/Nystromformer.

Nyströmformer: A Nyströmform-Based Algorithm for Approximating Self-Attention

Previous theory work on multi-objective evolutionary algorithms considers mostly easy problems that are composed of unimodal objectives. This paper takes a first step towards a deeper understanding of how evolutionary algorithms solve multi-modal multi-objective problems. We propose the OneJumpZeroJump problem, a bi-objective problem whose single objectives are isomorphic to the classic jump functions benchmark. We prove that the simple evolutionary multi-objective optimizer (SEMO) cannot compute the full Pareto front. In contrast, for all problem sizes n and all jump sizes k in [4..n/2-1], the global SEMO (GSEMO) covers the Pareto front in Î˜((n-2k)n^k) iterations in expectation. To improve the performance, we combine the GSEMO with two approaches, a heavy-tailed mutation operator and a stagnation detection strategy, that showed advantages in single-objective multi-modal problems. Runtime improvements of asymptotic order at least k^Î©(k) are shown for both strategies. Our experiments verify the substantial runtime gains already for moderate problem sizes. Overall, these results show that the ideas recently developed for single-objective evolutionary algorithms can be effectively employed also in multi-objective optimization.

Theoretical Analyses of Multi-Objective Evolutionary Algorithms on Multi-Modal Objectives

IQ -- Incremental Learning for Solving QSAT

Network embedding is aimed at mapping nodes in a network into low-dimensional vector representations. Graph Neural Networks (GNNs) have received widespread attention and lead to state-of-the-art performance in learning node representations. However, most GNNs only work in unsigned networks, where only positive links exist. It is not trivial to transfer these models to signed directed networks, which are widely observed in the real world yet less studied. In this paper, we first review two fundamental sociological theories (i.e., status theory and balance theory) and conduct empirical studies on real-world datasets to analyze the social mechanism in signed directed networks. Guided by related socio- logical theories, we propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks. The proposed model simultaneously reconstructs link signs, link directions, and signed directed triangles. We validate our modelâ€™s effectiveness on five real-world datasets, which are commonly used as the benchmark for signed network embeddings. Experiments demonstrate the proposed model outperforms existing models, including feature-based methods, network embedding methods, and several GNN methods.

SDGNN: Learning Node Representation for Signed Directed Networks

Hawkes processes have been shown to be efficient in modeling bursty
sequences in a variety of applications, such as finance and social network activity analysis.
Traditionally, these models parameterize each process independently and assume that
the history of each point process can be fully observed.
Such models could however be inefficient or even prohibited in certain real-world
applications, such as in the field of education, where such assumptions are violated.    
Motivated by the problem of detecting and predicting student procrastination in students Massive Open Online Courses (MOOCs) with missing and partially observed data, in this work, we propose a novel personalized Hawkes process model (RCHawkes-Gamma) that discovers meaningful student behavior clusters by jointly learning all partially observed processes simultaneously, without relying on auxiliary features.
Our experiments on both synthetic and real-world education datasets show that RCHawkes-Gamma can effectively recover student clusters and their temporal procrastination dynamics, resulting in better predictive performance of future student activities.
Our further analyses of the learned parameters and their association with student delays show that the discovered student clusters unveil meaningful representations of various procrastination behaviors in students.

Relaxed Clustered Hawkes Process for Student Procrastination Modeling in MOOCs

Contract scheduling is a general technique that allows to design a system with interruptible capabilities, given an algorithm that is not necessarily interruptible. Previous work on this topic has largely assumed that the interruption is a worst-case deadline that is unknown to the scheduler. In this work, we study the setting in which there is a potentially erroneous prediction concerning the interruption. Specifically, we consider the setting in which the prediction describes the time that the interruption occurs, as well as the setting in which the prediction is obtained as a response to a single or multiple binary queries. For both settings, we investigate tradeoffs between the robustness (i.e., the worst-case performance assuming adversarial prediction) and the consistency (i.e, the performance assuming that the prediction is error-free), both from the side of positive and negative results.

Contract Scheduling with Predictions

A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn dialogue modeling, the pre-trained language models (PrLMs) as encoder represent the dialogues coarsely by taking the pairwise dialogue history and candidate response as a whole, the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose a novel model to fill such a gap by modeling the effective utterance-aware and speaker-aware representations entailed in a dialogue history. In detail, we decouple the contextualized word representations by masking mechanisms in Transformer-based PrLM, making each word only focus on the words in current utterance, other utterances, two speaker roles (i.e., utterances of sender and utterances of receiver), respectively. Experimental results show that our method boosts the strong ELECTRA baseline substantially in four public benchmark datasets, and achieves various new state-of-the-art performance over previous methods. A series of ablation studies are conducted to demonstrate the effectiveness of our method.

Filling the Gap of Utterance-Aware and Speaker-Aware Representation for Multi-Turn Dialogue

This paper considers a video caption generating network referred to as Semantic Grouping Network (SGN) that attempts (1) to group video frames with discriminating word phrases of partially decoded caption and then (2) to decode those semantically aligned groups in predicting the next word. As consecutive frames are not likely to provide unique information, prior methods have focused on discarding or merging repetitive information based only on the input video. The SGN learns an algorithm to capture the most discriminating word phrases of the partially decoded caption and a mapping that associates each phrase to the relevant video frames - establishing this mapping allows semantically related frames to be clustered, which reduces redundancy. In contrast to the prior methods, the continuous feedback from decoded words enables the SGN to dynamically update the video representation that adapts to the partially decoded caption. Furthermore, a contrastive attention loss is proposed to facilitate accurate alignment between a word phrase and video frames without manual annotations. The SGN achieves state-of-the-art performances by outperforming runner-up methods by a margin of 2.1%p and 2.4%p in a CIDEr-D score on MSVD and MSR-VTT datasets, respectively. Extensive experiments demonstrate the effectiveness and interpretability of the SGN.

Semantic Grouping Network for Video Captioning

Monocular estimation of three dimensional human self-contact is fundamental for detailed scene analysis including body language understanding and behaviour modeling. 
Existing 3d reconstruction methods do not focus on body regions in self-contact and consequently recover configurations that are either far from each other or self-intersecting, when they should just touch. This leads to perceptually incorrect estimates and limits impact in those very fine-grained analysis domains where detailed 3d models are expected to play an important role. To address such challenges we detect self-contact and design 3d losses to explicitly enforce it. Specifically, we develop a model for Self-Contact Prediction (SCP), that estimates the body surface signature of self-contact, leveraging the localization of self-contact in the image, during both training and inference. We collect two large datasets to support learning and evaluation: (1) HumanSC3D, an accurate 3d motion capture repository containing 1,032 sequences with 5,058 contact events and 1,246,487 ground truth 3d poses synchronized with images collected from multiple views, and (2) FlickrSC3D, a repository of 3,969 images, containing 25,297 surface-to-surface correspondences with annotated image spatial support. We also illustrate how more expressive 3d reconstructions can be recovered under self-contact signature constraints and present monocular detection of face-touch as one of the multiple applications made possible by more accurate self-contact models.

Downloads

Next from AAAI 2021

Certifying Parity Reasoning Efficiently Using Pseudo-Boolean Proofs

Similar lecture

Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction

.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

Certifying Parity Reasoning Efficiently Using Pseudo-Boolean Proofs

Similar lecture

Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction

Downloads