word2vec.h File Reference

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Functions
void	LearnEmbeddings (TVVec< TInt, int64 > &WalksVV, const int &Dimensions, const int &WinSize, const int &Iter, const bool &Verbose, TIntFltVH &EmbeddingsHV)
	Learns embeddings using SGD, Skip-gram with negative sampling. More...

Variables
const int	MaxExp = 6
const int	ExpTablePrecision = 10000
const int	TableSize = MaxExp*ExpTablePrecision*2
const int	NegSamN = 5
const double	StartAlpha = 0.025

Function Documentation

void LearnEmbeddings	(	TVVec< TInt, int64 > &	WalksVV,
		const int &	Dimensions,
		const int &	WinSize,
		const int &	Iter,
		const bool &	Verbose,
		TIntFltVH &	EmbeddingsHV
	)

Learns embeddings using SGD, Skip-gram with negative sampling.

Definition at line 160 of file word2vec.cpp.

References THash< TKey, TDat, THashFunc >::AddDat(), TMath::E, ExpTablePrecision, THash< TKey, TDat, THashFunc >::GetDat(), TVVec< TVal, TSizeTy >::GetXDim(), TVVec< TVal, TSizeTy >::GetYDim(), InitNegEmb(), InitPosEmb(), InitUnigramTable(), THash< TKey, TDat, THashFunc >::IsKey(), LearnVocab(), MaxExp, TMath::Power(), StartAlpha, TableSize, and TrainModel().

Referenced by node2vec().

                           {
  TIntIntH RnmH;
  TIntIntH RnmBackH;
  int64 NNodes = 0;
  //renaming nodes into consecutive numbers
  for (int i = 0; i < WalksVV.GetXDim(); i++) {
    for (int64 j = 0; j < WalksVV.GetYDim(); j++) {
      if ( RnmH.IsKey(WalksVV(i, j)) ) {
        WalksVV(i, j) = RnmH.GetDat(WalksVV(i, j));
      } else {
        RnmH.AddDat(WalksVV(i,j),NNodes);
        RnmBackH.AddDat(NNodes,WalksVV(i, j));
        WalksVV(i, j) = NNodes++;
      }
    }
  }
  TIntV Vocab(NNodes);
  LearnVocab(WalksVV, Vocab);
  TIntV KTable(NNodes);
  TFltV UTable(NNodes);
  TVVec<TFlt, int64> SynNeg;
  TVVec<TFlt, int64> SynPos;
  TRnd Rnd(time(NULL));
  InitPosEmb(Vocab, Dimensions, Rnd, SynPos);
  InitNegEmb(Vocab, Dimensions, SynNeg);
  InitUnigramTable(Vocab, KTable, UTable);
  TFltV ExpTable(TableSize);
  double Alpha = StartAlpha;                              //learning rate
#pragma omp parallel for schedule(dynamic)
  for (int i = 0; i < TableSize; i++ ) {
    double Value = -MaxExp + static_cast<double>(i) / static_cast<double>(ExpTablePrecision);
    ExpTable[i] = TMath::Power(TMath::E, Value);
  }
  int64 WordCntAll = 0;
// op RS 2016/09/26, collapse does not compile on Mac OS X
//#pragma omp parallel for schedule(dynamic) collapse(2)
  for (int j = 0; j < Iter; j++) {
#pragma omp parallel for schedule(dynamic)
    for (int64 i = 0; i < WalksVV.GetXDim(); i++) {
      TrainModel(WalksVV, Dimensions, WinSize, Iter, Verbose, KTable, UTable,
       WordCntAll, ExpTable, Alpha, i, Rnd, SynNeg, SynPos); 
    }
  }
  if (Verbose) { printf("\n"); fflush(stdout); }
  for (int64 i = 0; i < SynPos.GetXDim(); i++) {
    TFltV CurrV(SynPos.GetYDim());
    for (int j = 0; j < SynPos.GetYDim(); j++) { CurrV[j] = SynPos(i, j); }
    EmbeddingsHV.AddDat(RnmBackH.GetDat(i), CurrV);
  }
}

Here is the call graph for this function:

Here is the caller graph for this function:

Variable Documentation

const int ExpTablePrecision = 10000

Definition at line 13 of file word2vec.h.

Referenced by LearnEmbeddings(), and TrainModel().

const int MaxExp = 6

Definition at line 10 of file word2vec.h.

Referenced by LearnEmbeddings(), LogSumExp(), TrainModel(), TMAGFitBern::UpdateApxPhiMI(), TMAGFitBern::UpdatePhi(), and TMAGFitBern::UpdatePhiMI().

const int NegSamN = 5

Definition at line 17 of file word2vec.h.

Referenced by TrainModel().

const double StartAlpha = 0.025

Definition at line 20 of file word2vec.h.

Referenced by LearnEmbeddings(), and TrainModel().

const int TableSize = MaxExp*ExpTablePrecision*2

Definition at line 14 of file word2vec.h.

Referenced by LearnEmbeddings(), and TrainModel().